© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10305
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters, with a focus on ampersands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.61
     unſ
    -0.57
    bootstrapcdn
    -0.55
    archiviato
    -0.52
     Anſ
    -0.50
     Infórmanos
    -0.50
     [$
    -0.50
    endpush
    -0.49
     —
    -0.48
     ſever
    -0.48
    POSITIVE LOGITS
    boneca
    0.46
    Географиясе
    0.45
     ilgili
    0.43
    Carcinogenicity
    0.42
     Getränke
    0.41
     mogelijkheid
    0.40
    Bioaccumulative
    0.40
    éroport
    0.40
    botines
    0.40
    Население
    0.39
    Activations Density 0.919%

    No Known Activations