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. 12-GEMMASCOPE-RES-16K
    6. 6508
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to statistical methods and assumptions in graphical models

    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
     LUMP
    -0.80
    umenical
    -0.71
     برانيه
    -0.71
     Mev
    -0.70
    ).-
    -0.69
    stdbool
    -0.68
    ])):
    -0.65
    :");
    -0.63
    ')")
    -0.63
    Geplaatst
    -0.62
    POSITIVE LOGITS
     SRA
    0.95
     SN
    0.91
    getS
    0.91
     S
    0.91
     getS
    0.90
     SBA
    0.85
     SAK
    0.84
     Sweeney
    0.83
     Sarmiento
    0.83
     Snyder
    0.83
    Activations Density 2.255%

    No Known Activations