© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11671
    Prev
    Next
    INDEX
    Explanations

    references to legal or political processes and decisions

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

    Language indicating future plans, announcements, or anticipated events, particularly phrases like "will," "expected to," "likely to," and "plans to" that signal upcoming actions or developments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of planned or potential actions and transactions—forward-looking news about appointments, bids/deals, trades, mergers/partnerships, and product launches.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.60
    clusão
    -0.59
    queryInterface
    -0.56
    ReusableCell
    -0.56
    WaitGroup
    -0.54
    WriteTagHelper
    -0.52
     amitié
    -0.51
     biografias
    -0.51
     oreja
    -0.51
    XmlAccessType
    -0.51
    POSITIVE LOGITS
    saraba
    0.38
    NameInMap
    0.36
     ممكن
    0.31
     Real
    0.31
     LONG
    0.31
     мѣ
    0.31
    hub
    0.30
    Hub
    0.30
    GEBURTSDATUM
    0.30
     possi
    0.30
    Activations Density 0.742%

    No Known Activations