© 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. 24-GEMMASCOPE-RES-16K
    11. 13757
    Prev
    Next
    INDEX
    Explanations

    mentions of opportunities or chances for beneficial actions or changes

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

    Tokens preceding infinitives related to "opportunity"

    np_acts-logits-general · gemini-2.0-flash

    opportunity arises or presented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    userdetails
    -0.47
    autoconfigure
    -0.44
    TestBed
    -0.41
    IMENTAL
    -0.41
    anthemum
    -0.40
    ATURA
    -0.40
    ThroughAttribute
    -0.40
    TypedArray
    -0.40
    chee
    -0.39
    pleaños
    -0.39
    POSITIVE LOGITS
     afforded
    0.96
     presented
    0.95
    presented
    0.86
     kasarigan
    0.84
    Opportunities
    0.81
     PRESENTED
    0.80
     arise
    0.79
     MainAxisSize
    0.79
     arises
    0.79
     exists
    0.79
    Activations Density 0.167%

    No Known Activations