Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 14802
    Prev
    Next
    INDEX
    Explanations

    instances of high-stakes digital security threats or vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.85
    '],
    
    -0.78
    "),
    
    -0.73
    '),
    
    -0.73
    ')")
    -0.71
    )':
    -0.71
    )";
    
    -0.71
    '")
    -0.71
    styleType
    -0.70
    "]);
    
    -0.69
    POSITIVE LOGITS
     majorité
    0.61
    ..
    0.59
     alimentaire
    0.58
    …
    0.57
     perchè
    0.57
     neder
    0.55
     metales
    0.54
    UnsafeEnabled
    0.54
     esser
    0.54
    !
    0.53
    Activations Density 0.338%

    No Known Activations