© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13140
    Prev
    Next
    INDEX
    Explanations

    HTML or web-related markup elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.47
    __':
    -0.42
     незавершена
    -0.42
    archiviato
    -0.40
    y
    -0.39
    <bos>
    -0.38
    oug
    -0.36
     Gries
    -0.36
    '");
    -0.35
    :+:
    -0.35
    POSITIVE LOGITS
    span
    1.18
    Span
    0.89
    TextSpan
    0.88
     span
    0.87
    SPAN
    0.85
    spans
    0.85
     Span
    0.84
     SPAN
    0.82
    MessageTagHelper
    0.70
     bershka
    0.69
    Activations Density 0.117%

    No Known Activations