© 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. 6051
    Prev
    Next
    INDEX
    Explanations

    important concepts related to communication and information exchange

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

    phrases or statements that indicate something is important or of significant interest.

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

    words or phrases indicating something is valuable, significant, or worthy of attention.

    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
    usermodel
    -0.49
     translateY
    -0.41
    PointerException
    -0.41
    ConstraintMaker
    -0.41
    styleType
    -0.40
    UnsafeEnabled
    -0.39
    ExecuteNonQuery
    -0.39
    colo
    -0.39
     OMITBAD
    -0.38
    BibitemShut
    -0.38
    POSITIVE LOGITS
     kepada
    1.69
    kepada
    1.12
    แก่
    1.07
     unto
    1.06
     to
    1.03
     vnto
    1.03
     aos
    0.97
     στους
    0.81
    tothe
    0.81
     åt
    0.77
    Activations Density 1.087%

    No Known Activations