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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 6866
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and mathematical relationships in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.67
     lccn
    -0.65
     <=",
    -0.60
    Personensuche
    -0.54
    })));
    -0.50
     nakalista
    -0.50
     كومونز
    -0.49
    PerformLayout
    -0.49
    NewReader
    -0.49
     VizieR
    -0.49
    POSITIVE LOGITS
     S
    1.14
     s
    0.98
    S
    0.95
     SS
    0.92
     SB
    0.87
     SR
    0.83
     SG
    0.83
     sulfur
    0.81
     SC
    0.81
    SS
    0.81
    Activations Density 2.609%

    No Known Activations