© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15779
    Prev
    Next
    INDEX
    Explanations

    references to claims and evidence supporting arguments

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

    nouns that represent concrete objects or entities placed in prepositional phrases.

    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
    eradish
    -0.47
     怎样
    -0.39
     appelez
    -0.35
    ografija
    -0.35
    DockStyle
    -0.35
     isSet
    -0.33
    delwed
    -0.32
    asteroide
    -0.32
    drawn
    -0.32
    imab
    -0.31
    POSITIVE LOGITS
     into
    0.69
     onto
    0.66
     closer
    0.59
    Ӕ
    0.56
     squarely
    0.53
    Composable
    0.52
     defaultstate
    0.52
     firmly
    0.52
    endregion
    0.51
     astray
    0.49
    Activations Density 0.209%

    No Known Activations