© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 10670
    Prev
    Next
    INDEX
    Explanations

    elements related to account management and navigation in a user interface

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

    instructional or procedural text that describes how to navigate user interface elements and complete specific tasks.

    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
    xrLabel
    -0.24
     initial
    -0.24
    localctx
    -0.23
    chlag
    -0.22
     final
    -0.21
    parseFrom
    -0.21
    xlim
    -0.21
    вгения
    -0.21
    OuterAlt
    -0.21
    Genau
    -0.21
    POSITIVE LOGITS
     settings
    0.81
     logout
    0.78
     Settings
    0.77
     utafitiHapana
    0.75
     SETTINGS
    0.75
    ChangePassword
    0.74
     Profile
    0.73
     Logout
    0.73
    Settings
    0.73
    SETTINGS
    0.72
    Activations Density 0.168%

    No Known Activations