© 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. 28-GEMMASCOPE-RES-16K
    11. 7997
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions

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

    Code snippets, especially JavaScript

    np_acts-logits-general · gemini-2.0-flash

    code or script snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.56
     propOrder
    -0.49
    SharedCtor
    -0.46
    🔕
    -0.44
    onames
    -0.43
    typeorm
    -0.43
    曖昧さ回避
    -0.40
    Brainz
    -0.40
    estacks
    -0.40
    enumii
    -0.39
    POSITIVE LOGITS
     scripts
    0.75
     script
    0.73
     Script
    0.62
     snippets
    0.62
     Scripts
    0.61
     scripting
    0.60
     text
    0.59
    script
    0.59
     code
    0.58
     scri
    0.55
    Activations Density 0.974%

    No Known Activations