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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8402
    Prev
    Next
    INDEX
    Explanations

    terms related to molecular biology and cancer research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     joining
    -0.34
     specialized
    -0.33
     fickle
    -0.32
    Specialized
    -0.31
    nanoTime
    -0.31
    äu
    -0.31
     teaming
    -0.31
     specializing
    -0.30
     strapless
    -0.30
     Kämp
    -0.30
    POSITIVE LOGITS
    AndEndTag
    0.81
    ⓧ
    0.78
    ladder
    0.70
     виправивши
    0.67
    Ladder
    0.67
     MW
    0.66
     ladder
    0.66
    mw
    0.66
     nahilalakip
    0.65
     صوتيه
    0.65
    Activations Density 1.050%

    No Known Activations