© 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. 9867
    Prev
    Next
    INDEX
    Explanations

    technical terms related to cellular networks and communication infrastructure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    geographic or spatial boundaries, particularly regions, zones, or areas with distinct properties.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     avancé
    -0.25
    '
    -0.24
     Saturday
    -0.23
     SATURDAY
    -0.23
     teacher
    -0.23
    先
    -0.23
     Friday
    -0.23
     or
    -0.22
    FromArray
    -0.22
    <strong>
    -0.21
    POSITIVE LOGITS
    setVerticalGroup
    1.03
    tagHelperRunner
    0.99
    webElementXpaths
    0.98
     zone
    0.98
     Zones
    0.93
     Zone
    0.93
     zones
    0.91
    Zone
    0.88
    zone
    0.87
    zones
    0.86
    Activations Density 0.688%

    No Known Activations