© 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. 20-GEMMASCOPE-RES-16K
    11. 7906
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing or adding elements to a discussion or context

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

    "Mix" or "picture"

    np_acts-logits-general · gemini-2.0-flash

    in the picture, out of the mix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WebDriverWait
    -0.94
    OGND
    -0.88
     تضيفلها
    -0.81
     itſelf
    -0.76
    LookAnd
    -0.76
    UnusedPrivate
    -0.75
     myſelf
    -0.74
     ſeveral
    -0.71
     >=",
    -0.71
    IntoConstraints
    -0.70
    POSITIVE LOGITS
     equation
    1.38
     mix
    1.30
    equation
    0.98
    mix
    0.95
     picture
    0.92
     Equation
    0.92
     Mix
    0.92
    Mix
    0.92
     equations
    0.88
     mixes
    0.85
    Activations Density 0.184%

    No Known Activations