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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 673
    Prev
    Next
    INDEX
    Explanations

    highly frequent or common punctuation marks and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.71
     $_(
    -0.56
    webElementXpaths
    -0.52
     $_"
    -0.52
     محفوظة
    -0.52
     AssemblyTitle
    -0.48
     Waſſer
    -0.48
     Geſ
    -0.48
    Tikang
    -0.48
     ſind
    -0.47
    POSITIVE LOGITS
    uxxxx
    0.53
    http
    0.46
     [...]
    0.45
    https
    0.45
    <eos>
    0.44
    .[/
    0.44
    続きを読む
    0.42
    Lire
    0.42
     […]
    0.42
    […]
    0.42
    Activations Density 0.496%

    No Known Activations