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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 10653
    Prev
    Next
    INDEX
    Explanations

    specific terms and names, particularly related to semiconductor technology and associated measurements

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

    short, lowercase subword fragments—often two-letter sequences—and common snake_case prefixes in code/technical contexts.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    й
    -1.10
    一个
    -0.92
    йки
    -0.87
     Sapi
    -0.83
     Bartol
    -0.82
    kém
    -0.81
     manufact
    -0.81
     Baldwin
    -0.77
    Gott
    -0.77
     dale
    -0.77
    POSITIVE LOGITS
     Lynd
    0.89
     soeur
    0.89
     nationaux
    0.85
     sabbia
    0.84
    ly
    0.84
     suivie
    0.84
    に
    0.82
     Landis
    0.78
     Rha
    0.77
    hoeddwyd
    0.76
    Activations Density 1.398%

    No Known Activations