Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10653
    Prev
    Next
    INDEX
    Explanations

    data related to statistical analysis and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __).
    -0.54
    __);
    -0.49
    potranspiration
    -0.49
    endforeach
    -0.47
     useAuth
    -0.46
    ']->
    -0.46
    ')),
    -0.43
    тери
    -0.42
    ']),
    -0.41
    )));
    
    -0.41
    POSITIVE LOGITS
     propOrder
    0.91
     OnTriggerEnter
    0.80
    ########.
    0.73
     betweenstory
    0.72
     ProtoMessage
    0.65
     smtplib
    0.63
     Signalez
    0.62
    ValueStyle
    0.62
     COVERAGE
    0.62
     Majefty
    0.61
    Activations Density 1.834%

    No Known Activations