© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 6667
    Prev
    Next
    INDEX
    Explanations

    specific terms related to data structures and statistical methods

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

    numerical comparisons and quantities in technical and scientific contexts.

    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
     épaules
    -0.43
     judiciales
    -0.41
     dangereux
    -0.40
     Grecs
    -0.38
    jednoc
    -0.38
     puits
    -0.37
     religiosos
    -0.37
     religiosas
    -0.36
     gafas
    -0.36
     dorada
    -0.36
    POSITIVE LOGITS
     complexes
    0.76
     mga
    0.75
     agendas
    0.75
     catalogues
    0.75
     histories
    0.75
     budgets
    0.74
     catalogs
    0.74
     palettes
    0.74
     websites
    0.71
     regimes
    0.71
    Activations Density 2.802%

    No Known Activations