© 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. 20-GEMMASCOPE-RES-16K
    6. 6158
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters associated with experiments or studies

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

    technical medical research details and numerical measurements.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    section and subsection numbering patterns in academic documents.

    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
    +#+
    -0.85
    OCCURRED
    -0.84
    UserScript
    -0.81
    rungsseite
    -0.77
    ModelSerializer
    -0.76
    AddTagHelper
    -0.75
    WebElementEntity
    -0.71
    ⓧ
    -0.71
    principalColumn
    -0.68
     Italijani
    -0.68
    POSITIVE LOGITS
    })()
    0.38
    })`
    0.36
    nativeElement
    0.35
    })));
    0.33
    səhifə
    0.33
    fører
    0.32
     pizarra
    0.32
     referido
    0.32
     undermining
    0.32
     captioned
    0.32
    Activations Density 0.052%

    No Known Activations