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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16232
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to indexing and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.58
     purpoſe
    -0.54
    Przypisy
    -0.52
    ſelves
    -0.49
     المعيارى
    -0.47
     ſever
    -0.47
     '\\;'
    -0.47
     Tér
    -0.47
    gemeen
    -0.46
     Reſ
    -0.46
    POSITIVE LOGITS
     IndexPath
    0.69
    HasIndex
    0.54
    NSIndexPath
    0.50
    IndexPath
    0.50
     position
    0.48
    setVerticalGroup
    0.46
    tonode
    0.46
    =$((
    0.45
    findIndex
    0.43
     index
    0.43
    Activations Density 0.561%

    No Known Activations