© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1206
    Prev
    Next
    INDEX
    Explanations

    connections to biological structures and their interactions, particularly in relation to risk factors and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ็จ
    -0.76
    InjectAttribute
    -0.75
    TypedDataSet
    -0.74
     HasFactory
    -0.74
    [])
    
    -0.71
    SequentialGroup
    -0.71
    MessageOf
    -0.71
    ########.
    -0.70
    )$/,
    -0.70
    AccessorTable
    -0.69
    POSITIVE LOGITS
     or
    0.71
    거나
    0.65
     alebo
    0.59
    或
    0.54
     atau
    0.53
     или
    0.53
     eller
    0.53
    或者
    0.51
     who
    0.50
     või
    0.50
    Activations Density 0.738%

    No Known Activations