© 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. 31-GEMMASCOPE-RES-16K
    6. 12327
    Prev
    Next
    INDEX
    Explanations

    specific details regarding screenshots or screen captures in a context

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

    references to screenshots or visual images being displayed or referenced in technical documentation.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.47
    StructEnd
    -0.45
    odeon
    -0.42
    ergies
    -0.41
    󠁴
    -0.40
     Obrador
    -0.40
    sonian
    -0.40
     Normdatei
    -0.40
    bibitem
    -0.39
     setType
    -0.39
    POSITIVE LOGITS
     screenshot
    2.03
     screenshots
    1.98
     screen
    1.95
     Screenshot
    1.76
     SCREEN
    1.76
     Screen
    1.71
     screens
    1.68
     Screenshots
    1.67
    Screenshot
    1.66
    Screen
    1.61
    Activations Density 0.352%

    No Known Activations