© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 39190
    Prev
    Next
    INDEX
    Explanations

    phrases related to the construction of grammatical sentences

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

    einen kor / das Honig / das Ver / これを 売

    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
    Kariera
    -0.50
    __(/*!
    -0.49
    __*/
    -0.47
    rscheinlichkeit
    -0.43
     وتسجيلات
    -0.42
    AccessorTable
    -0.40
     JpaRepository
    -0.40
    Filmographie
    -0.40
     Numerade
    -0.40
    UpInside
    -0.39
    POSITIVE LOGITS
     Administrativna
    0.55
    把
    0.49
    getDescriptor
    0.43
     pylint
    0.43
     leaſt
    0.43
    chränk
    0.43
    addComponent
    0.41
     把
    0.40
     leſs
    0.40
    stylers
    0.39
    Activations Density 0.092%

    No Known Activations