© 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. 10-GEMMASCOPE-RES-16K
    11. 10608
    Prev
    Next
    INDEX
    Explanations

    phrases and questions that initiate or emphasize a discussion on opinions and conditions related to knowledge, responsibility, and expectations

    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
     Soria
    -0.60
    annica
    -0.60
     seksual
    -0.59
    척
    -0.56
     Bhutan
    -0.56
    nością
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    chte
    -0.53
     sexual
    -0.53
    clays
    -0.52
    POSITIVE LOGITS
    whats
    1.02
     whats
    0.93
    Whats
    0.91
     wireType
    0.88
    AndEndTag
    0.76
     Réponses
    0.72
     Whats
    0.72
     springfox
    0.69
    Према
    0.67
    ::::::::::::::::
    0.65
    Activations Density 0.127%

    No Known Activations