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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4371
    Prev
    Next
    INDEX
    Explanations

    phrases about characters and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.95
    MENAFN
    -0.79
     متعلقه
    -0.68
    
    -0.67
     препратки
    -0.64
    }\]
    -0.63
    ])));
    -0.62
     dignité
    -0.61
    '));
    
    -0.61
    UnusedPrivate
    -0.60
    POSITIVE LOGITS
     Nickelodeon
    0.64
     girl
    0.62
     teen
    0.62
     teens
    0.58
     teenage
    0.55
     teenagers
    0.55
    iettes
    0.53
     brunette
    0.53
     crushes
    0.53
     rainbows
    0.52
    Activations Density 0.224%

    No Known Activations