© 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. 15899
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions and consequences in legal or procedural contexts

    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
     незавершена
    -0.70
     للمعارف
    -0.69
     irgende
    -0.57
     algún
    -0.54
     comuniques
    -0.54
     žád
    -0.53
     يتيمه
    -0.53
    ագրություններ
    -0.52
    もしれない
    -0.51
    bootstrapcdn
    -0.50
    POSITIVE LOGITS
     firstly
    0.95
     einerseits
    0.89
    :
    0.82
    :
    0.73
     both
    0.72
     Firstly
    0.71
    :")
    0.70
    ①
    0.69
    Firstly
    0.69
     ①
    0.69
    Activations Density 1.359%

    No Known Activations