© 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. 8040
    Prev
    Next
    INDEX
    Explanations

    dependencies and conditions related to coding or programming concepts

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

    contrasting statements between a first and second item or approach.

    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
    Filmographie
    -0.40
    IsMutable
    -0.39
    oa̍t
    -0.38
    今まで
    -0.37
    IsContent
    -0.36
    nsito
    -0.36
    éraires
    -0.35
     ändå
    -0.35
     typelib
    -0.35
    tyfik
    -0.34
    POSITIVE LOGITS
     second
    3.33
    second
    2.92
     secondly
    2.59
    Second
    2.59
     SECOND
    2.55
     Second
    2.44
     segundo
    2.39
     segunda
    2.39
    SECOND
    2.38
    Secondly
    2.38
    Activations Density 1.358%

    No Known Activations