© 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. 15-GEMMASCOPE-RES-16K
    11. 3080
    Prev
    Next
    INDEX
    Explanations

    function definitions and their properties in code

    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
    √
    -0.45
    ker
    -0.43
    sch
    -0.43
    ni
    -0.43
    Total
    -0.43
    See
    -0.43
     total
    -0.42
    see
    -0.40
     See
    -0.40
     Total
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    5.70
    contentLoaded
    1.52
     defaultstate
    1.50
     noqa
    1.47
    matchCondition
    1.44
     صوتيه
    1.33
    MemoryWarning
    1.28
    ResumeLayout
    1.28
    __":
    1.27
    UnknownFields
    1.26
    Activations Density 0.006%

    No Known Activations