© 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. 10-GEMMASCOPE-RES-16K
    6. 1812
    Prev
    Next
    INDEX
    Explanations

    terms related to HTTP responses and status handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENDIAN
    -0.65
    Buk
    -0.63
    тельстве
    -0.63
     Buk
    -0.61
    gley
    -0.60
     let
    -0.57
     plat
    -0.57
     defaultstate
    -0.56
    AsUp
    -0.56
    NewGuid
    -0.56
    POSITIVE LOGITS
     responses
    1.71
     response
    1.67
     Response
    1.62
     Responses
    1.55
     RESPONSE
    1.54
    response
    1.51
    Responses
    1.49
    Response
    1.44
    RESPONSE
    1.40
    responses
    1.39
    Activations Density 0.091%

    No Known Activations