© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 3231
    Prev
    Next
    INDEX
    Explanations

    statements indicating a person's title or role within an organization

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

    "is", often followed by adjectives describing someone

    np_acts-logits-general · gemini-2.0-flash

    is followed by quality or role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Données
    -0.56
     taget
    -0.54
    chay
    -0.52
    EndContext
    -0.49
    IVEREF
    -0.47
    IBOutlet
    -0.47
     derniers
    -0.47
     sabato
    -0.46
    Contours
    -0.46
    PerformLayout
    -0.45
    POSITIVE LOGITS
     proud
    0.66
     convinced
    0.60
    rungsseite
    0.58
     adept
    0.56
    passen
    0.55
    __":
    0.54
    proud
    0.54
    <!--[
    0.53
     privy
    0.53
    tempted
    0.52
    Activations Density 0.235%

    No Known Activations