© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13890
    Prev
    Next
    INDEX
    Explanations

    physical descriptors and materials used in crafting or manipulating objects

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

    Materials or tools

    np_acts-logits-general · gemini-2.0-flash

    masking tape pieces

    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
    findpost
    -0.71
    LookAnd
    -0.64
     /*#__
    -0.62
     setw
    -0.59
    migrationBuilder
    -0.59
    GraphicsUnit
    -0.58
     Roskov
    -0.58
     hwnd
    -0.56
    InjectAttribute
    -0.56
     venons
    -0.55
    POSITIVE LOGITS
     old
    0.76
     masking
    0.71
     dow
    0.68
     Sty
    0.63
     cardboard
    0.61
     painters
    0.61
     piece
    0.59
     Masking
    0.59
    masking
    0.59
     sty
    0.58
    Activations Density 0.213%

    No Known Activations