© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 7079
    Prev
    Next
    INDEX
    Explanations

    logical operators, particularly conjunctions and disjunctions, commonly used in programming and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    -0.66
    y
    -0.62
     Elias
    -0.60
    imag
    -0.59
    ます
    -0.59
    iz
    -0.57
    The
    -0.57
    прочем
    -0.56
    mente
    -0.55
    cal
    -0.55
    POSITIVE LOGITS
     &&
    1.60
    &&&&
    1.53
    &&
    1.44
    )&&
    1.38
    &&&
    1.37
    &&\
    1.36
    InjectAttribute
    1.17
     &=&
    1.02
    )&&(
    0.99
     &&
    0.96
    Activations Density 0.030%

    No Known Activations