© 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. 4-GEMMASCOPE-RES-16K
    6. 15682
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions describing time, amounts, or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     './
    -0.46
    êng
    -0.45
     "./
    -0.45
    ["_
    -0.43
    SID
    -0.43
    tonode
    -0.43
     fyr
    -0.43
     ['./
    -0.42
    Schule
    -0.42
    zonego
    -0.41
    POSITIVE LOGITS
    enumi
    0.95
     thousands
    0.84
     tens
    0.82
     hundreds
    0.81
    thousands
    0.79
     Hundreds
    0.77
    hundreds
    0.75
    Portály
    0.75
    ousands
    0.74
    AsUp
    0.74
    Activations Density 0.343%

    No Known Activations