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. 15618
    Prev
    Next
    INDEX
    Explanations

    comparisons involving numerical thresholds

    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
    Clik
    -0.79
    l
    -0.73
     l
    -0.67
    man
    -0.67
    t
    -0.65
    ीस
    -0.65
    let
    -0.65
    ess
    -0.64
    ิมพ์
    -0.64
     düş
    -0.63
    POSITIVE LOGITS
    ]>=
    1.37
    )>=
    1.25
     >=
    1.22
    >=
    1.08
     Majefty
    0.95
     againſt
    0.95
    bibfield
    0.91
     myſelf
    0.90
    StateToProps
    0.90
     Efq
    0.88
    Activations Density 0.122%

    No Known Activations