© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 43079
    Prev
    Next
    INDEX
    Explanations

    URLs and web links related to information sources

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

    URLs and technical words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </i>
    -0.41
    </b>
    -0.38
    </code>
    -0.34
    </em>
    -0.32
     ...
    -0.32
    </u>
    -0.29
       
    -0.27
     [
    -0.26
    </h3>
    -0.25
    ...
    -0.25
    POSITIVE LOGITS
    tagHelperRunner
    1.23
    ValueStyle
    1.20
    principalTable
    1.13
     utafitiHapana
    1.11
    Билгалдахарш
    1.05
    AsUp
    1.03
    fjspx
    1.02
    AndEndTag
    0.98
     EconPapers
    0.98
    styleType
    0.97
    Activations Density 0.016%

    No Known Activations