© 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. 31-GEMMASCOPE-RES-16K
    11. 8743
    Prev
    Next
    INDEX
    Explanations

    references to formal submissions and approvals in the context of festivals or contests

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

    formal submission and acceptance language in official documents.

    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
    SharedCtor
    -0.47
    SpringBootTest
    -0.43
    UnitTesting
    -0.40
    rawDesc
    -0.39
     GenerationType
    -0.39
    IntoConstraints
    -0.36
    getDoctrine
    -0.36
    matchCondition
    -0.36
    nesia
    -0.36
    ształ
    -0.36
    POSITIVE LOGITS
     submitted
    2.73
     submission
    2.72
     submit
    2.56
     submissions
    2.52
     submitting
    2.50
     submits
    2.34
     Submit
    2.33
     Submission
    2.30
    Submit
    2.19
    submit
    2.17
    Activations Density 0.678%

    No Known Activations