© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8240
    Prev
    Next
    INDEX
    Explanations

    elements related to numerical or structural references in code

    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
     '\\;'
    -0.54
    Rhestr
    -0.54
    ChildScrollView
    -0.52
     PeEnEo
    -0.50
    下载附件
    -0.50
    astify
    -0.50
     CURIAM
    -0.49
    featureID
    -0.49
     occaf
    -0.48
     ſal
    -0.48
    POSITIVE LOGITS
    ########.
    0.48
     kautta
    0.39
     soeur
    0.36
    endforeach
    0.35
    componentWill
    0.35
    Przypisy
    0.34
    ">//
    0.34
     Pres
    0.33
     kanssa
    0.31
    각주
    0.31
    Activations Density 0.051%

    No Known Activations