© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 4232
    Prev
    Next
    INDEX
    Explanations

    certain symbols and notations, particularly caret characters and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.68
    RTLR
    -0.63
    createCanvas
    -0.62
    tvguidetime
    -0.61
    FailureListener
    -0.59
    الدراسه
    -0.59
    UnitTesting
    -0.58
    Datuak
    -0.57
    ########.
    -0.56
    TemporalType
    -0.56
    POSITIVE LOGITS
     ↑
    1.98
    ↑
    0.70
    //
    0.62
     ^
    0.51
    ↑↑
    0.44
     AssemblyTitle
    0.43
     the
    0.41
     Audiodateien
    0.39
    <td>
    0.39
    ❋
    0.39
    Activations Density 0.025%

    No Known Activations