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. 12-GEMMASCOPE-RES-16K
    6. 100
    Prev
    Next
    INDEX
    Explanations

    structural elements and observations related to data or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.81
    setVerticalGroup
    -0.65
    featureID
    -0.63
    iffion
    -0.63
     Meksiku
    -0.62
     Italijanski
    -0.62
    Vidite
    -0.61
    skull
    -0.60
    ówczas
    -0.59
    Biblia
    -0.59
    POSITIVE LOGITS
    br
    0.51
    dflare
    0.50
    Service
    0.45
     appar
    0.44
    chia
    0.44
    Hochspringen
    0.44
     MainAxisSize
    0.43
     excellent
    0.43
    Great
    0.42
     Great
    0.42
    Activations Density 0.216%

    No Known Activations