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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12556
    Prev
    Next
    INDEX
    Explanations

    patterns and functions related to data structures and operations in programming

    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
     theirs
    -1.55
     mine
    -1.46
     yours
    -1.42
    Mine
    -1.36
     ours
    -1.36
     hers
    -1.34
     Mine
    -1.26
     Yours
    -1.17
    mine
    -1.17
     MINE
    -1.15
    POSITIVE LOGITS
     EconPapers
    0.60
     disponibilités
    0.56
    irchen
    0.56
    EditorBrowsable
    0.49
    ніципалі
    0.49
    orsese
    0.48
    ]")]
    0.48
    rogels
    0.47
     Wicidata
    0.47
    estias
    0.46
    Activations Density 0.310%

    No Known Activations