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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9274
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to coding or programming

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

    Code snippets or mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    async data callbacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.55
    RetentionPolicy
    -0.47
     Thor
    -0.47
     sarili
    -0.46
     Almost
    -0.46
     förr
    -0.46
     Photocase
    -0.46
    StoryboardSegue
    -0.45
    pushFollow
    -0.44
     Aruba
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.69
     &___
    0.41
    OCCURRED
    0.35
     tartalomajánló
    0.33
    </thead>
    0.31
     зру
    0.30
     discorso
    0.30
    WebVitals
    0.30
    hoeddwyd
    0.30
    signal
    0.29
    Activations Density 0.059%

    No Known Activations