© 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. 9690
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and action verbs indicating usage or involvement

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

    has been / is not / has died

    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
    photobucket
    -0.38
     Metzger
    -0.38
    Datuak
    -0.38
     étrang
    -0.37
     nomme
    -0.36
     exécu
    -0.36
     licenci
    -0.36
     Irán
    -0.35
    retweeted
    -0.35
     are
    -0.35
    POSITIVE LOGITS
    VersionUID
    0.57
    Демографія
    0.56
    IsMutable
    0.54
    <?
    0.53
     Außerdem
    0.53
    şört
    0.52
     Bewußt
    0.52
     gewiß
    0.51
     Pristupljeno
    0.51
    tanleria
    0.51
    Activations Density 0.101%

    No Known Activations