© 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. 22-GEMMASCOPE-RES-16K
    6. 3644
    Prev
    Next
    INDEX
    Explanations

    the prefix "inter" indicating intersections or interactions across concepts

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

    The token "inter"

    np_acts-logits-general · gemini-2.0-flash

    words starting with inter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.74
    :✨
    -0.65
    InputBorder
    -0.61
    GraphicsUnit
    -0.55
     transfieras
    -0.54
    memoized
    -0.53
     wireType
    -0.53
    )))
    
    -0.53
    resave
    -0.52
    neming
    -0.52
    POSITIVE LOGITS
     inter
    0.75
     Inter
    0.69
    Inter
    0.69
     INTER
    0.61
     generational
    0.60
     Inters
    0.54
    (&:
    0.53
    este
    0.53
     changeable
    0.52
    lock
    0.51
    Activations Density 0.103%

    No Known Activations