© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3428
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to data structures, encryption, and computational processes

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

    hyphenated compound words and technical reference citations.

    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
     gostar
    -0.53
     buurt
    -0.48
     fotografico
    -0.47
     goederen
    -0.46
     mít
    -0.46
     afbeelding
    -0.46
     esquecer
    -0.46
     mijne
    -0.46
     achtergrond
    -0.45
     muur
    -0.45
    POSITIVE LOGITS
    EndContext
    0.76
    /-
    0.62
    withstanding
    0.56
    StructEnd
    0.56
     IBOutlet
    0.56
    ViewImports
    0.52
    Geplaatst
    0.52
    ScopeManager
    0.50
    Rptr
    0.50
    theless
    0.49
    Activations Density 2.579%

    No Known Activations