© 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. 1-GEMMASCOPE-RES-16K
    6. 14706
    Prev
    Next
    INDEX
    Explanations

    numeric values and identifiers related to data or measurement entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )");
    
    -0.93
    rungsseite
    -0.87
    RectangleBorder
    -0.82
    )");
    -0.76
    tvguidetime
    -0.76
    mybatisplus
    -0.75
    oredCriteria
    -0.74
    AddHtmlAttribute
    -0.74
    KURZBESCHREIBUNG
    -0.73
    queryInterface
    -0.73
    POSITIVE LOGITS
    -
    0.56
     
    0.53
     -
    0.50
    ALLEL
    0.47
     مبارک
    0.46
     hexagonal
    0.46
    θλη
    0.46
     individuality
    0.45
     atheists
    0.45
     Kopf
    0.44
    Activations Density 0.418%

    No Known Activations