© 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. 18-GEMMASCOPE-RES-16K
    6. 6683
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sentences."

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

    Text after punctuation

    np_acts-logits-general · gemini-2.0-flash

    dining establishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     moule
    -0.64
    '));
    
    -0.60
    s
    -0.58
    remadura
    -0.55
    belline
    -0.55
    ¿½
    -0.53
    ]();
    -0.53
    sio
    -0.52
    허
    -0.52
     Cod
    -0.51
    POSITIVE LOGITS
     DINNER
    0.95
     Dinner
    0.91
     dinners
    0.89
     dinner
    0.85
    তথ্যসূত্র
    0.84
    GIH
    0.80
    dinner
    0.76
    Dinner
    0.74
    Ethnicity
    0.74
     restaurants
    0.73
    Activations Density 0.084%

    No Known Activations