© 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. 3-GEMMASCOPE-RES-16K
    6. 760
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to physics and scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.57
    ViewImports
    -0.52
    QPalette
    -0.49
    IMHO
    -0.46
    istoitu
    -0.44
    HasForeignKey
    -0.44
    Ikus
    -0.44
    Aiheesta
    -0.44
    GARET
    -0.44
     Seh
    -0.43
    POSITIVE LOGITS
    +#+
    0.88
    UnknownFieldSet
    0.69
    DockStyle
    0.68
    Portale
    0.63
    stdc
    0.62
    بوابة
    0.60
    ArgumentParser
    0.59
     öffnungszeiten
    0.59
    Abitanti
    0.58
    :+:
    0.58
    Activations Density 1.405%

    No Known Activations