Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12791
    Prev
    Next
    INDEX
    Explanations

    conjugated forms of the verb "to have" in various contexts

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

    First-person pronouns in French, Spanish, or Portuguese

    np_acts-logits-general · gemini-2.0-flash

    avoir or ter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.89
    setVerticalGroup
    -0.83
     المعيارى
    -0.72
    хьтан
    -0.67
    bewerken
    -0.64
    PickerController
    -0.63
    awtextra
    -0.61
    Datuak
    -0.61
     CGSize
    -0.61
    GoogleApiClient
    -0.61
    POSITIVE LOGITS
     toques
    0.46
    ρίες
    0.46
    many
    0.45
    his
    0.45
     mucha
    0.42
     tanta
    0.41
    出版年
    0.40
     grandes
    0.40
     Siegel
    0.39
     great
    0.39
    Activations Density 0.044%

    No Known Activations