© 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. 1-GEMMASCOPE-RES-16K
    6. 9017
    Prev
    Next
    INDEX
    Explanations

    mentions of substances or materials associated with pharmaceuticals or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jumps
    -0.46
     defaultstate
    -0.45
     morango
    -0.43
     jump
    -0.42
    lusconi
    -0.41
    @+
    -0.40
    Приятного
    -0.40
     degeneracy
    -0.39
    flame
    -0.39
    adaptiveStyles
    -0.39
    POSITIVE LOGITS
    ub
    0.84
    UB
    0.61
    Yard
    0.59
     disciplina
    0.58
    IndentedString
    0.57
     discipline
    0.57
     Yard
    0.56
     DISCIP
    0.55
    putchar
    0.55
     yard
    0.54
    Activations Density 0.305%

    No Known Activations