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. 13108
    Prev
    Next
    INDEX
    Explanations

    components related to flavor profiles in beverages

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

    taste/flavor/smell

    np_acts-logits-general · gemini-2.0-flash

    flavors and qualities

    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
    DrawerToggle
    -0.73
    IntoConstraints
    -0.65
     regla
    -0.51
    SqlClient
    -0.51
    Lij
    -0.50
    GeneratedCode
    -0.50
     eorum
    -0.50
     quæ
    -0.50
     gneiss
    -0.49
     licorne
    -0.49
    POSITIVE LOGITS
     kasarigan
    0.78
     complexity
    0.72
     balanced
    0.71
     الرياضيه
    0.68
     balance
    0.67
     <=",
    0.67
    balanced
    0.65
     équilibr
    0.63
    OrBuilder
    0.62
     hints
    0.62
    Activations Density 0.050%

    No Known Activations