© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2147
    Prev
    Next
    INDEX
    Explanations

    code snippets and structure related to programming or software development

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

    Code snippets or code-related formatting

    np_acts-logits-general · gemini-2.0-flash

    code block endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.77
    ########.
    -0.77
     transfieras
    -0.74
    MigrationBuilder
    -0.72
    principalColumn
    -0.71
    Chham
    -0.67
    expandindo
    -0.63
    Portail
    -0.63
    RRect
    -0.62
    IVEREF
    -0.62
    POSITIVE LOGITS
    </em>
    1.68
    </strong>
    1.31
    </u>
    1.26
    </code>
    1.19
    </i>
    1.15
    </h4>
    1.07
    </h5>
    1.06
    </blockquote>
    1.04
    </h2>
    1.03
    </h3>
    1.00
    Activations Density 0.074%

    No Known Activations