© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8774
    Prev
    Next
    INDEX
    Explanations

    technical documentation or code-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.78
    \",\
    -0.71
    MLLoader
    -0.69
    \"");
    -0.66
    */}
    -0.66
    andExpect
    -0.65
    withIdentifier
    -0.65
     surla
    -0.62
     <",
    -0.60
    。】
    -0.59
    POSITIVE LOGITS
    </em>
    1.00
    </blockquote>
    0.89
    </code>
    0.78
    </strong>
    0.69
    <strong>
    0.64
    <em>
    0.61
    </h5>
    0.60
    </s>
    0.56
    </i>
    0.52
    <code>
    0.49
    Activations Density 0.105%

    No Known Activations