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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12620
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional or subjective states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.91
    "]);
    
    -0.90
    ")));
    
    -0.87
    styleType
    -0.84
    '}>
    -0.83
    }")
    
    -0.82
     وتسجيلات
    -0.81
    "]).
    -0.81
    ).
    
    -0.80
    ?».
    -0.80
    POSITIVE LOGITS
    !
    0.94
    ,
    0.83
     and
    0.60
    .
    0.60
     now
    0.59
    ;
    0.57
    !!
    0.56
     right
    0.55
     too
    0.55
    !!!
    0.55
    Activations Density 0.517%

    No Known Activations