© 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. 14183
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "scope" in various contexts

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

    The token "scope"

    np_acts-logits-general · gemini-2.0-flash

    scope

    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
    ConstraintMaker
    -0.67
     Silverman
    -0.65
    </b>
    -0.64
    esModule
    -0.64
     PackageManager
    -0.64
    CrossRef
    -0.63
    usermodel
    -0.62
    exitRule
    -0.61
    parte
    -0.59
    牌
    -0.58
    POSITIVE LOGITS
     scopes
    1.45
     scope
    1.44
     SCOPE
    1.36
     Scope
    1.35
    scope
    1.26
    scopes
    1.21
    Scope
    1.14
    Scopes
    1.03
    SCOPE
    0.98
    coroutines
    0.93
    Activations Density 0.099%

    No Known Activations