© 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. 15-GEMMASCOPE-RES-16K
    6. 2025
    Prev
    Next
    INDEX
    Explanations

    references to government or policy discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whilst
    -0.73
    Whilst
    -0.70
     ostavi
    -0.69
    !";
    -0.66
     ایشان
    -0.65
    IsMutable
    -0.64
    に於
    -0.63
     whilst
    -0.63
    جوايز
    -0.63
    "],
    
    -0.62
    POSITIVE LOGITS
     lawmakers
    0.67
     POLIT
    0.61
     <<<<<<<<<<<<<<
    0.58
    principalColumn
    0.55
     investigators
    0.55
     —
    0.54
    Искәрмәләр
    0.53
     Inscrivez
    0.53
     lawmaker
    0.52
     ftate
    0.52
    Activations Density 0.235%

    No Known Activations