© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 974
    Prev
    Next
    INDEX
    Explanations

    values and measurements related to experimental data

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Mentions "initial" or change from "baseline"

    np_acts-logits-general · gemini-2.0-flash

    initial value or baseline

    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
    Negative Logits
    ⓧ
    -0.56
    CELLANEOUS
    -0.41
     autorytatywna
    -0.41
     ब्रेकडाउन
    -0.38
    UGHS
    -0.38
    oa̍t
    -0.38
     Abp
    -0.38
     الحره
    -0.36
    TypedDataSet
    -0.36
     فريبيس
    -0.36
    POSITIVE LOGITS
     initial
    1.81
     Initial
    1.61
    initial
    1.58
    Initial
    1.52
    初始
    1.49
     initially
    1.47
     inicial
    1.45
     initiale
    1.44
     INITIAL
    1.41
     Initially
    1.36
    Activations Density 1.552%

    No Known Activations