© 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. 4-GEMMASCOPE-RES-16K
    11. 3714
    Prev
    Next
    INDEX
    Explanations

    references to planning activities or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    logram
    -0.73
    providedIn
    -0.70
    vatar
    -0.68
    posedge
    -0.66
    vertx
    -0.64
    XmlEnum
    -0.61
    DebuggerStep
    -0.60
    toPromise
    -0.59
    ucap
    -0.58
    tonode
    -0.57
    POSITIVE LOGITS
     planning
    2.25
     Planning
    2.20
    Planning
    2.06
    planning
    2.01
     PLANNING
    1.99
     planners
    1.73
     Planners
    1.61
     planner
    1.52
     planification
    1.41
     Planner
    1.40
    Activations Density 0.136%

    No Known Activations