© 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. 4-GEMMASCOPE-RES-16K
    11. 12861
    Prev
    Next
    INDEX
    Explanations

    affirmative or assertive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.71
     Jefus
    -1.68
     purpoſe
    -1.63
     Efq
    -1.61
     Monfieur
    -1.61
     houſe
    -1.60
     ſche
    -1.56
     Majefty
    -1.55
     Chriftian
    -1.51
     myſelf
    -1.48
    POSITIVE LOGITS
     not
    0.71
     G
    0.60
     stato
    0.58
     es
    0.57
     the
    0.57
    </i>
    0.56
     La
    0.56
     ra
    0.56
     il
    0.55
     a
    0.55
    Activations Density 0.210%

    No Known Activations