© 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. 534
    Prev
    Next
    INDEX
    Explanations

    statements reflecting confidence and belief in various claims or facts

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

    verbs expressing cognitive processes or statements of belief and knowledge.

    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
     linkovi
    -0.55
    Derbyniad
    -0.53
     Италијани
    -0.50
    AnimationsModule
    -0.50
    WithIOException
    -0.50
     jScrollPane
    -0.48
     autorytatywna
    -0.48
    AccessorTable
    -0.47
    protoimpl
    -0.46
    يكب
    -0.45
    POSITIVE LOGITS
     they
    1.54
     we
    1.30
     she
    1.16
     he
    1.03
     there
    1.02
     it
    0.84
     you
    0.83
    they
    0.82
     theyre
    0.77
     они
    0.75
    Activations Density 0.701%

    No Known Activations