© 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. 17-GEMMASCOPE-RES-16K
    6. 4902
    Prev
    Next
    INDEX
    Explanations

    sequences of parentheses or brackets that indicate the structure of expressions or functions in programming code

    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
    帖最后由
    -0.86
    ̯
    -0.81
    venus
    -0.75
    ing
    -0.73
    MatInputModule
    -0.73
     Biôgrafia
    -0.72
    shah
    -0.72
     SYS
    -0.71
     Loth
    -0.69
    toolStrip
    -0.69
    POSITIVE LOGITS
    ))
    1.08
    ]))
    0.87
    )),
    0.82
    ()))
    0.78
    __))
    0.77
    )){
    0.77
    )));
    0.76
    ]],
    0.74
    ));
    0.74
    ]]
    0.73
    Activations Density 0.401%

    No Known Activations