© 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. 25-GEMMASCOPE-RES-16K
    11. 2944
    Prev
    Next
    INDEX
    Explanations

    punctuation or sentence-ending marks within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    periods and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     she
    -1.73
    she
    -1.50
     we
    -1.32
     he
    -1.30
    She
    -1.14
     they
    -1.13
    we
    -1.12
    they
    -1.10
    We
    -1.03
    He
    -1.03
    POSITIVE LOGITS
    wendigkeit
    0.52
    élev
    0.51
    cipais
    0.50
    lotz
    0.50
    🎰
    0.48
    Odkazy
    0.48
    Portály
    0.48
    Legende
    0.48
    ovem
    0.48
    abbé
    0.47
    Activations Density 0.455%

    No Known Activations