© 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. 1970
    Prev
    Next
    INDEX
    Explanations

    references to cooperative strategies or frameworks

    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
     EAT
    -0.84
    mort
    -0.71
    eat
    -0.69
    fas
    -0.69
    fist
    -0.69
    Eat
    -0.68
    EAT
    -0.66
     poffible
    -0.66
     OCLC
    -0.65
    sidian
    -0.65
    POSITIVE LOGITS
     scheme
    1.98
    Scheme
    1.98
     SCHEME
    1.96
     schemes
    1.95
    scheme
    1.93
     Scheme
    1.89
     Schemes
    1.85
    schemes
    1.83
    SCHEME
    1.80
    Schemes
    1.76
    Activations Density 0.097%

    No Known Activations