© 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. 24-GEMMASCOPE-RES-16K
    6. 1912
    Prev
    Next
    INDEX
    Explanations

    mention of government or political figures, specifically in relation to their statements or actions

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

    Follows a person's title or name

    np_acts-logits-general · gemini-2.0-flash

    names after roles, american cultures

    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
    uio
    -0.51
    vistar
    -0.46
    演
    -0.45
    Madagascar
    -0.45
    SWIG
    -0.43
     Bengaluru
    -0.43
    vcut
    -0.42
     SPRINGS
    -0.41
    ijn
    -0.41
    kuuta
    -0.41
    POSITIVE LOGITS
    SizeMode
    0.75
     Maher
    0.72
     Fa
    0.67
     Bader
    0.67
    \{\\
    0.65
    CloseOperation
    0.64
    Sale
    0.63
     виправивши
    0.63
    expandindo
    0.61
     Salem
    0.61
    Activations Density 0.111%

    No Known Activations