© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 7869
    Prev
    Next
    INDEX
    Explanations

    references to programming and file structure

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

    markup and code structure elements like HTML tags, LaTeX package declarations, and programming language function signatures.

    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
     Wikimedijinoj
    -0.59
    IsMutable
    -0.58
    findpost
    -0.56
    OrNil
    -0.53
     CreateTagHelper
    -0.51
     unknownFields
    -0.48
    routeProvider
    -0.47
     DBNull
    -0.47
     invokingState
    -0.47
    twimg
    -0.46
    POSITIVE LOGITS
    المكان
    0.52
     probes
    0.45
     घ
    0.41
     Fry
    0.41
     fatos
    0.40
     utaf
    0.39
     Probes
    0.39
     Grä
    0.38
    zany
    0.38
     graça
    0.38
    Activations Density 0.297%

    No Known Activations