© 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. 8005
    Prev
    Next
    INDEX
    Explanations

    language related to legal discussions and labor relations

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

    Comes after uncommon symbols/characters

    np_acts-logits-general · gemini-2.0-flash

    percentages, percentages, chemical notations, biological 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
    ".
    
    -0.69
    $.
    
    -0.61
    ")));
    
    -0.57
    )";
    
    -0.52
     Chwiliwch
    -0.51
    .";
    
    -0.51
    UnknownFieldSet
    -0.50
    `,
    
    -0.47
     kaarangay
    -0.47
    WebElementEntity
    -0.46
    POSITIVE LOGITS
     ↑
    1.26
     →
    1.16
    ▼
    1.15
     <<
    1.09
     ⇒
    1.07
     ›
    1.07
     ||
    1.05
     ≈
    1.03
     ◆
    1.03
     >>
    1.01
    Activations Density 10.925%

    No Known Activations