© 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. 21-GEMMASCOPE-RES-16K
    6. 2595
    Prev
    Next
    INDEX
    Explanations

    references to specific names and affiliations within a text

    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
     fato
    -0.51
     Dunlap
    -0.50
     promedio
    -0.50
     redor
    -0.48
     câncer
    -0.48
    Nbr
    -0.46
     contato
    -0.43
     gotten
    -0.42
     tienden
    -0.42
     comunicarse
    -0.41
    POSITIVE LOGITS
    
    0.95
     Efq
    0.90
     Theſe
    0.78
     myſelf
    0.74
     Forumite
    0.74
     actionMode
    0.72
     MBE
    0.70
     Chriftian
    0.70
    abestanden
    0.67
     Audiodateien
    0.67
    Activations Density 0.165%

    No Known Activations