© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 13040
    Prev
    Next
    INDEX
    Explanations

    occurrences of the expression "ha" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.43
     ModelExpression
    -0.40
     isNameExpr
    -0.40
     afecto
    -0.36
    empor
    -0.36
     vora
    -0.36
     asemenea
    -0.35
    grö
    -0.35
     demás
    -0.35
     щ
    -0.35
    POSITIVE LOGITS
     ha
    0.60
    Ha
    0.53
     Ha
    0.51
    MenuInflater
    0.45
     haiku
    0.43
    Demografie
    0.43
     hama
    0.42
    ContentLoaded
    0.41
     дописавши
    0.41
    JAKARTA
    0.40
    Activations Density 0.227%

    No Known Activations