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. 14-GEMMASCOPE-RES-16K
    6. 12915
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements and conditions in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.85
    HideFlags
    -0.75
    adopt
    -0.72
     purpoſe
    -0.68
    oa̍t
    -0.68
    ########.
    -0.67
    +#+#
    -0.66
    berdayakan
    -0.65
    存于互联网档案馆
    -0.63
     marquées
    -0.62
    POSITIVE LOGITS
     during
    0.57
    waitKey
    0.54
    DeleteBehavior
    0.53
     daily
    0.49
    HandlerContext
    0.47
     routine
    0.47
     delivery
    0.47
    stdc
    0.46
     recorded
    0.45
    lijkse
    0.44
    Activations Density 1.586%

    No Known Activations