© 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. 14030
    Prev
    Next
    INDEX
    Explanations

    references to the term "Arch" and its related variations, indicating a focus on architecture or hierarchical structures

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

    words beginning with "Arch" (such as "Archbishop," "Archdeacon," "Architecture," etc.).

    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
    ESA
    -0.35
    esa
    -0.35
    ren
    -0.34
     rever
    -0.33
    stdc
    -0.33
    m
    -0.33
    UnitTesting
    -0.33
    inste
    -0.33
    aneous
    -0.32
    providedIn
    -0.32
    POSITIVE LOGITS
     Arch
    0.78
     arch
    0.76
     ARCH
    0.72
    Arch
    0.66
     Archi
    0.66
     Arches
    0.63
     arches
    0.62
     Архи
    0.61
     Arco
    0.60
     archi
    0.60
    Activations Density 0.142%

    No Known Activations