© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 558
    Prev
    Next
    INDEX
    Explanations

    HTML or code snippets related to web development concepts

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

    before numbers

    np_acts-logits-general · gemini-2.0-flash

    technical contexts and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.68
    ⓧ
    -0.66
    fjspx
    -0.64
     للاسماء
    -0.64
    ftagPool
    -0.61
    utilisons
    -0.56
    makeConstraints
    -0.56
     perchè
    -0.56
     cherchés
    -0.56
    ientí
    -0.54
    POSITIVE LOGITS
     XNUMX
    0.84
    NUMX
    0.73
     ​​
    0.61
     .;
    0.49
    ̵
    0.47
     .:
    0.45
    ​​
    0.42
     voorbij
    0.39
    Citiți
    0.38
     ™
    0.38
    Activations Density 0.068%

    No Known Activations