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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 5443
    Prev
    Next
    INDEX
    Explanations

    elements related to legal proceedings and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TextAppearance
    -0.73
    principalColumn
    -0.59
    ItemBackground
    -0.58
    MessageOf
    -0.58
    enterOuterAlt
    -0.56
     '\\;'
    -0.53
    FunctionFlags
    -0.53
     nakalista
    -0.52
    addCriterion
    -0.50
    aarrggbb
    -0.49
    POSITIVE LOGITS
     before
    4.06
    before
    3.36
     antes
    3.17
     sebelum
    3.11
     Before
    3.08
    Before
    3.06
     ennen
    2.84
     BEFORE
    2.77
     قبل
    2.67
     înainte
    2.66
    Activations Density 3.379%

    No Known Activations