© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15126
    Prev
    Next
    INDEX
    Explanations

    references to awareness, recognition, and observation of specific details or features

    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
    atever
    -0.58
    hdashline
    -0.56
    Cordialement
    -0.55
     hoffen
    -0.55
     ब्रेकडाउन
    -0.55
     отношению
    -0.55
    ErrUnexpectedEOF
    -0.55
    othesis
    -0.54
    calaureate
    -0.53
    tover
    -0.53
    POSITIVE LOGITS
     adanya
    0.70
     similarities
    0.69
     deficiencies
    0.65
     imperfections
    0.63
     differences
    0.63
     discrepancies
    0.63
     difference
    0.63
     StringTokenizer
    0.62
     patterns
    0.61
     وتسجيلات
    0.61
    Activations Density 0.359%

    No Known Activations