© 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. 1-GEMMASCOPE-RES-16K
    6. 8044
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of "gain" or "acquisition."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ohs
    -0.59
     casco
    -0.59
     photographed
    -0.54
    Composable
    -0.50
    motic
    -0.50
    ographed
    -0.48
    デコ
    -0.48
    Whoops
    -0.48
    deco
    -0.48
    DOCTYPE
    -0.47
    POSITIVE LOGITS
     gain
    4.61
     Gain
    4.20
    gain
    4.08
    Gain
    3.93
     gained
    3.73
     gains
    3.64
     GAIN
    3.60
     gaining
    3.47
     Gains
    3.04
    gains
    3.04
    Activations Density 0.102%

    No Known Activations