© 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. 2114
    Prev
    Next
    INDEX
    Explanations

    key players and their performances in sports

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

    preceding a conjunction or preposition

    np_acts-logits-general · gemini-2.0-flash

    performance status and struggles

    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
    )}</
    -0.67
    !*\
    -0.56
     rhestr
    -0.55
    olusi
    -0.51
     democrática
    -0.50
    tilor
    -0.49
    Välislingid
    -0.49
    Marshaller
    -0.49
    ])));
    -0.48
    />
    
    -0.48
    POSITIVE LOGITS
     offensively
    1.06
     defensively
    0.83
     heading
    0.77
     late
    0.71
     afield
    0.69
     entering
    0.67
     early
    0.66
     against
    0.65
     down
    0.64
    featureID
    0.63
    Activations Density 0.195%

    No Known Activations