© 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. 2560
    Prev
    Next
    INDEX
    Explanations

    instructions or actions related to retrieving items or fulfilling requests

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

    actions or movements of objects or people being brought, carried, or moved into or inside a location.

    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
    bootstrapcdn
    -0.43
     елның
    -0.32
    最快更新
    -0.32
    RTLD
    -0.31
    hueta
    -0.30
    下载附件
    -0.29
    vertret
    -0.28
    chaqueta
    -0.28
    ourable
    -0.28
    AnchorTagHelper
    -0.27
    POSITIVE LOGITS
     inside
    3.22
     Inside
    2.95
    Inside
    2.94
    inside
    2.92
     INSIDE
    2.75
    INSIDE
    2.48
     interior
    2.45
     внутри
    2.42
     internal
    2.39
     insides
    2.33
    Activations Density 0.902%

    No Known Activations