© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9259
    Prev
    Next
    INDEX
    Explanations

    affirmative statements and words that denote actions or states

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    it followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.32
    CodeAnalysis
    -0.26
    andingan
    -0.25
    Kanpo
    -0.24
    isNullOrEmpty
    -0.22
    ../
    -0.22
    CodeAttribute
    -0.20
    andaan
    -0.20
     juntas
    -0.20
    …
    -0.20
    POSITIVE LOGITS
    rungsseite
    1.02
    LookAnd
    0.84
     HasFactory
    0.74
    AddHtmlAttribute
    0.72
     ſind
    0.72
    niſſe
    0.70
     magasiner
    0.70
    ðsíða
    0.69
     müſſen
    0.69
    complexContent
    0.68
    Activations Density 0.658%

    No Known Activations