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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 23-GEMMASCOPE-RES-131K
    6. 23111
    Prev
    Next
    INDEX
    Explanations

    concepts related to therapy and treatment programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.96
     Infórmanos
    -0.91
    httphttps
    -0.82
    .",
    
    -0.81
    .";
    
    -0.80
    tvguidetime
    -0.79
    DockStyle
    -0.78
    GEBURTSDATUM
    -0.78
    LEncoder
    -0.77
    <pad>
    -0.77
    POSITIVE LOGITS
    :
    0.42
    ,
    0.39
     наоборот
    0.29
    ?
    0.29
     revanche
    0.28
     lunares
    0.27
    )
    0.26
    .
    0.26
     Though
    0.26
    ;
    0.26
    Activations Density 0.042%

    No Known Activations