Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9084
    Prev
    Next
    INDEX
    Explanations

    programming constructs and error handling terms related to API registration and validation

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

    error handling and validation logic in code.

    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
     initComponents
    -0.52
    LookAnd
    -0.50
     AssemblyCompany
    -0.49
     regioni
    -0.48
    webElementGuid
    -0.45
    PDOException
    -0.45
    ItemBackground
    -0.44
    CPtr
    -0.44
    Hentet
    -0.44
    AndroidJUnit
    -0.43
    POSITIVE LOGITS
    TryDecodeAsNil
    0.47
    appendix
    0.44
    contentLoaded
    0.40
    induction
    0.40
     postIndex
    0.40
     dAtA
    0.40
     XL
    0.38
    StringLen
    0.37
    appeal
    0.35
    setPrice
    0.35
    Activations Density 0.494%

    No Known Activations