© 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. 23-GEMMASCOPE-RES-16K
    11. 12725
    Prev
    Next
    INDEX
    Explanations

    names and titles of various individuals in entertainment and arts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.67
    IntoConstraints
    -0.55
    jsii
    -0.54
    ximate
    -0.52
    Diweddarwch
    -0.51
     للمعارف
    -0.51
    yntaxException
    -0.51
     preventiva
    -0.50
    บัติ
    -0.50
    avax
    -0.50
    POSITIVE LOGITS
     best
    1.70
     famous
    1.51
    best
    1.41
     known
    1.39
     famed
    1.29
    famous
    1.27
     better
    1.22
     renowned
    1.19
    known
    1.14
     bekannt
    1.13
    Activations Density 0.244%

    No Known Activations