© 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. 35-GEMMASCOPE-RES-16K
    11. 12959
    Prev
    Next
    INDEX
    Explanations

    themes of personal struggle and perseverance in overcoming challenges

    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
    省市镇
    -0.59
    ыгана
    -0.56
    دانشنامهٔ
    -0.56
    */;
    -0.54
     Administrativna
    -0.51
     oblige
    -0.51
    )++;
    -0.51
    ʖ
    -0.51
    ).[
    -0.50
     IIRC
    -0.48
    POSITIVE LOGITS
     sometimes
    0.66
     everyday
    0.61
     quotidien
    0.54
     mentally
    0.53
     constantly
    0.53
    sometimes
    0.52
     subconsciously
    0.51
     daily
    0.50
     unconsciously
    0.50
     Sometimes
    0.50
    Activations Density 0.659%

    No Known Activations