© 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. 13124
    Prev
    Next
    INDEX
    Explanations

    references to athletes and their achievements

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

    Follows ordinal numbers or superlatives

    np_acts-logits-general · gemini-2.0-flash

    competitions and games championships

    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
     protoimpl
    -0.58
     temps
    -0.45
     soccer
    -0.45
     race
    -0.45
    탈
    -0.44
    nesc
    -0.43
     Raffle
    -0.43
     Diesel
    -0.43
    ρών
    -0.43
     derby
    -0.42
    POSITIVE LOGITS
    ̍t
    0.72
    PropertyChanging
    0.62
    providedIn
    0.61
     initComponents
    0.60
     nakalista
    0.59
    TabIndex
    0.58
    abinieri
    0.57
    Personendaten
    0.57
    VIAF
    0.57
    ExtendWith
    0.56
    Activations Density 0.135%

    No Known Activations