© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9598
    Prev
    Next
    INDEX
    Explanations

    phrases related to food production and quality control

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

    temporal or seasonal events and transitions (harvest timing, migration periods, scheduled dates).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISupport
    -0.46
    EndInit
    -0.43
    のもと
    -0.38
     ब्रेकडाउन
    -0.38
     updateUser
    -0.38
    uário
    -0.38
     strijd
    -0.38
     illustrationer
    -0.37
    toMatchSnapshot
    -0.36
    Ligações
    -0.35
    POSITIVE LOGITS
     timing
    1.42
     Timing
    1.30
    Timing
    1.17
    timing
    1.11
     delayed
    1.06
     dates
    1.06
     delaying
    1.05
     timeline
    1.05
     earliest
    1.04
     timings
    1.04
    Activations Density 1.136%

    No Known Activations