© 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. 1935
    Prev
    Next
    INDEX
    Explanations

    emphasis on bodily or health-related conditions and environmental influences

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

    Tokens preceding units of time or quantities

    np_acts-logits-general · gemini-2.0-flash

    numerical and technical terms

    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
     satunya
    -0.77
     related
    -0.65
    verhält
    -0.61
    ichè
    -0.60
     এর
    -0.59
    erschein
    -0.59
    aaral
    -0.58
    antaranya
    -0.58
     coté
    -0.57
     hearted
    -0.56
    POSITIVE LOGITS
    -
    2.10
    -,
    1.00
    ‑
    0.96
    -/
    0.93
    -​
    0.89
    ‐
    0.83
    ®-
    0.80
    -
    
    0.78
    –
    0.78
    -“
    0.77
    Activations Density 1.003%

    No Known Activations