Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13934
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to biological and chemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following research findings

    np_acts-logits-general · gemini-2.0-flash

    obvious meanwhile observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.71
     ExecuteAsync
    -0.67
    RenderAtEndOf
    -0.67
    principalTable
    -0.64
    MLLoader
    -0.63
     OMITBAD
    -0.63
     typelib
    -0.59
     isNameExpr
    -0.59
    behaviour
    -0.56
    uxxxx
    -0.55
    POSITIVE LOGITS
     Meanwhile
    0.86
    Meanwhile
    0.77
     ①
    0.75
    Ⅰ
    0.72
    ①
    0.70
    
    0.70
     meanwhile
    0.70
     obvious
    0.69
    
    0.67
     obviously
    0.66
    Activations Density 2.389%

    No Known Activations