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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14078
    Prev
    Next
    INDEX
    Explanations

    structured mathematical expressions and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.69
     ब्रेकडाउन
    -0.61
    lliant
    -0.56
    createCanvas
    -0.56
     Boek
    -0.55
    expandindo
    -0.54
     Cune
    -0.54
     utafitiHapana
    -0.53
    eson
    -0.53
    SSP
    -0.52
    POSITIVE LOGITS
     \\
    0.99
     <<<<<<<<<<<<<<
    0.62
    </h4>
    0.57
     Audiodateien
    0.56
    </h5>
    0.53
    </h3>
    0.52
    <tr>
    0.52
    }\\
    0.50
    subsubsection
    0.49
     \\\
    0.49
    Activations Density 0.082%

    No Known Activations