© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14281
    Prev
    Next
    INDEX
    Explanations

    information related to sports teams, schedules, and statistics

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

    Sports statistics, standings, and data

    np_acts-logits-general · gemini-2.0-flash

    sports statistics and teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.64
     AssemblyCompany
    -0.63
    ponses
    -0.60
    avyzd
    -0.59
    ANTLR
    -0.59
    zzleHttp
    -0.58
    ########.
    -0.57
    ViewFeatures
    -0.55
    protoc
    -0.53
    ינוך
    -0.52
    POSITIVE LOGITS
     statistics
    0.98
     stats
    0.94
     standings
    0.89
     records
    0.83
     statistical
    0.81
     stat
    0.81
     match
    0.80
     Match
    0.77
     scores
    0.76
    statistics
    0.75
    Activations Density 0.241%

    No Known Activations