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. 7-GEMMASCOPE-RES-16K
    6. 4595
    Prev
    Next
    INDEX
    Explanations

    references to academic proceedings and conferences

    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
    )։
    -0.70
    ')],
    -0.70
    queryInterface
    -0.68
    ")));
    
    -0.66
    '):
    
    -0.65
     HasFactory
    -0.63
    ')));
    -0.63
    EDEFAULT
    -0.63
    )"),
    -0.61
     cuban
    -0.60
    POSITIVE LOGITS
     Proceedings
    1.40
    Proceedings
    1.25
     proceedings
    1.12
    ceedings
    1.04
     Proc
    0.99
     PROCEEDINGS
    0.92
     proceeding
    0.86
    Proc
    0.83
     Proceeding
    0.79
     proceeds
    0.74
    Activations Density 0.053%

    No Known Activations