© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10507
    Prev
    Next
    INDEX
    Explanations

    definitions and associations related to various scientific and medical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical and computational code-like syntax, such as hexadecimal values, programming defines, and hexadecimal memory addresses.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    parenthetical citation patterns for academic references with years around 2000-2007.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    hexadecimal numbers and numerical codes in technical documents.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.71
     snippetHide
    -0.52
     linkovi
    -0.51
    ➟
    -0.50
    twimg
    -0.48
     ModelExpression
    -0.48
    Edu
    -0.46
    Edi
    -0.46
    equ
    -0.46
    ので
    -0.45
    POSITIVE LOGITS
     A
    0.85
     А
    0.74
    appui
    0.61
    assemblée
    0.60
     Α
    0.60
    accompag
    0.60
    amitié
    0.59
    A
    0.59
    aménagement
    0.58
    Assemblée
    0.55
    Activations Density 2.205%

    No Known Activations