© 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. 94735
    Prev
    Next
    INDEX
    Explanations

    references to the term "Hak" and its variations in contexts related to names, places, or figures

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

    hak and hakem

    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
    orderItem
    -0.32
    line
    -0.31
    point
    -0.30
     mostrarse
    -0.29
    <tr>
    -0.29
    –
    -0.29
     ocupado
    -0.28
    ville
    -0.27
    .”
    -0.26
    liz
    -0.26
    POSITIVE LOGITS
    hak
    2.45
    Hak
    2.44
     Hak
    2.42
     hak
    1.97
     Hakim
    1.47
    haka
    1.41
    haku
    1.25
    Hack
    1.22
     hakk
    1.21
    haq
    1.20
    Activations Density 0.011%

    No Known Activations