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. 11189
    Prev
    Next
    INDEX
    Explanations

    data regarding player statistics and achievements in football

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

    Preceding names, often "John" or "He"

    np_acts-logits-general · gemini-2.0-flash

    appear, score, feature

    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
    uxxxx
    -0.78
     Audiodateien
    -0.74
     AssemblyCulture
    -0.69
     archivi
    -0.64
    remia
    -0.64
    Portale
    -0.61
     invade
    -0.60
    новниш
    -0.57
    TabIndex
    -0.57
     esternos
    -0.56
    POSITIVE LOGITS
     convocatoria
    0.53
     senior
    0.51
     fit
    0.49
     feature
    0.45
     REPRESENT
    0.45
    Scape
    0.45
     berücksichtigt
    0.44
    features
    0.44
    fasis
    0.43
     GenerationType
    0.43
    Activations Density 0.135%

    No Known Activations