© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3573
    Prev
    Next
    INDEX
    Explanations

    specific nouns and technical specifications related to products and their features

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

    after possessive pronouns/determiners

    np_acts-logits-general · gemini-2.0-flash

    possessive noun then noun

    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
     trol
    -0.61
     huts
    -0.58
    boxes
    -0.56
     Boxes
    -0.55
     PublicKey
    -0.54
     portfolios
    -0.54
     SUVs
    -0.54
    distas
    -0.54
     centers
    -0.52
     TVs
    -0.52
    POSITIVE LOGITS
     própri
    0.87
    expandindo
    0.82
     auroit
    0.71
     étoient
    0.69
    BeginContext
    0.68
     avoient
    0.67
     enfans
    0.67
     touristes
    0.67
     varandra
    0.66
     anún
    0.66
    Activations Density 0.953%

    No Known Activations