© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15
    Prev
    Next
    INDEX
    Explanations

    structured or formatted code and mathematical notations

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

    LaTeX math environment delimiters

    np_acts-logits-general · gemini-2.0-flash

    lemma followed by mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pica
    -0.57
     CDS
    -0.55
    seido
    -0.53
    ={<
    -0.52
     braid
    -0.52
     blister
    -0.51
     groom
    -0.50
     RIAA
    -0.50
    lito
    -0.50
     GMB
    -0.50
    POSITIVE LOGITS
    </blockquote>
    0.96
     Audiodateien
    0.85
     iconLine
    0.68
     intptr
    0.62
    </table>
    0.62
    \]
    0.60
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.57
    </h5>
    0.55
    <blockquote>
    0.54
    }-*/;
    0.54
    Activations Density 0.224%

    No Known Activations