© 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. 4782
    Prev
    Next
    INDEX
    Explanations

    statements related to uncertainty or verification of information

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

    expressions of uncertainty or imprecision about specific details or numbers.

    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
    expandindo
    -0.38
     normalidad
    -0.38
     habituales
    -0.36
     насељу
    -0.35
     делу
    -0.34
    endalikan
    -0.32
    Soorten
    -0.32
     prioridad
    -0.31
    GraphicsUnit
    -0.30
     clasificación
    -0.30
    POSITIVE LOGITS
     exact
    3.33
     exactly
    3.08
    exact
    3.02
     Exact
    2.89
    exactly
    2.88
    Exact
    2.73
     EXACT
    2.73
     EXACTLY
    2.70
     Exactly
    2.70
     precisely
    2.69
    Activations Density 0.731%

    No Known Activations