© 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. 18-GEMMASCOPE-RES-16K
    11. 1606
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to pioneering achievements or innovations

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

    "of its kind" or "ahead of its time"

    np_acts-logits-general · gemini-2.0-flash

    of its kind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithFormat
    -0.53
    rangle
    -0.48
    RetentionPolicy
    -0.48
    })`
    -0.48
    MigrationBuilder
    -0.46
     (;
    -0.45
    toFixed
    -0.44
    WindowConstants
    -0.43
     r
    -0.43
    DataURL
    -0.42
    POSITIVE LOGITS
     its
    0.98
     своего
    0.88
     своё
    0.84
    Its
    0.83
     svého
    0.83
    its
    0.78
     свое
    0.77
     своє
    0.76
     ihres
    0.75
     itſelf
    0.74
    Activations Density 0.093%

    No Known Activations