© 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-2-9B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 13817
    Prev
    Next
    INDEX
    Explanations

    instances of personal declarations or expressions of identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.94
    tvguidetime
    -0.90
     ſind
    -0.88
    iſen
    -0.81
    setViewportView
    -0.81
    GOTREF
    -0.79
     laſſen
    -0.77
     defaultstate
    -0.77
     ſein
    -0.77
     beſch
    -0.77
    POSITIVE LOGITS
    s
    1.23
    <bos>
    0.65
    t
    0.60
    ll
    0.54
    m
    0.54
    re
    0.48
     s
    0.48
    S
    0.47
    ls
    0.47
    ns
    0.44
    Activations Density 0.401%

    No Known Activations