© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 9134
    Prev
    Next
    INDEX
    Explanations

    conditional statements and hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.84
    ituary
    -0.78
    DispatchToProps
    -0.78
     jspb
    -0.77
     CommandType
    -0.77
    những
    -0.77
     lenker
    -0.76
    rrggbb
    -0.75
    MethodManager
    -0.75
    ("")){
    -0.73
    POSITIVE LOGITS
    Suppose
    0.94
     Suppose
    0.84
     suppose
    0.72
    ọi
    0.67
     Assume
    0.67
    Let
    0.64
     assume
    0.62
    假设
    0.59
     Let
    0.59
    Assume
    0.58
    Activations Density 0.829%

    No Known Activations