Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5853
    Prev
    Next
    INDEX
    Explanations

    expressions of personal reflection and emotional turmoil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insists
    -0.47
     kine
    -0.47
    uoco
    -0.46
     claiming
    -0.44
     `{
    -0.44
    --(
    -0.44
    ponenten
    -0.43
    {?>
    -0.43
     Pense
    -0.42
     considérons
    -0.42
    POSITIVE LOGITS
    TagMode
    0.84
    tvguidetime
    0.83
     وتسجيلات
    0.78
    ConstraintMaker
    0.73
     صوتيه
    0.73
    principalTable
    0.69
     StringTokenizer
    0.69
     дописавши
    0.68
    windowFixed
    0.67
    EndGlobalSection
    0.67
    Activations Density 0.197%

    No Known Activations