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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9923
    Prev
    Next
    INDEX
    Explanations

    specific months and significant dates

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

    Months of the year

    np_acts-logits-general · gemini-2.0-flash

    months and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    -0.43
    nb
    -0.42
    SharedCtor
    -0.41
    1
    -0.41
    roid
    -0.41
    2
    -0.40
    5
    -0.40
    male
    -0.40
     породы
    -0.39
    3
    -0.39
    POSITIVE LOGITS
     December
    0.74
     February
    0.72
     November
    0.71
     MMMM
    0.71
    December
    0.70
     September
    0.69
    ScopeManager
    0.68
     January
    0.68
     Month
    0.68
     October
    0.68
    Activations Density 0.093%

    No Known Activations