© 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. 23-GEMMASCOPE-RES-16K
    6. 6228
    Prev
    Next
    INDEX
    Explanations

    phrases related to authoritative assertions and recommendations

    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
     appelés
    -0.48
     fascination
    -0.45
     unsatisfied
    -0.44
     вот
    -0.43
    []
    -0.43
     normaux
    -0.43
    cydow
    -0.43
    ष्य
    -0.42
    intérêt
    -0.42
     tă
    -0.42
    POSITIVE LOGITS
     carefully
    0.80
    Lähteet
    0.73
     monitored
    0.73
     tightly
    0.72
     properly
    0.71
     adequately
    0.71
     subject
    0.70
     tailored
    0.70
    écnicas
    0.68
    subject
    0.67
    Activations Density 0.587%

    No Known Activations