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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 6293
    Prev
    Next
    INDEX
    Explanations

    syntactic structure in HTML or code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.64
    swick
    -0.61
     fondue
    -0.58
    AddTagHelper
    -0.57
     IFTT
    -0.57
    ัพท์
    -0.57
     ModelExpression
    -0.56
    Дереккөздер
    -0.56
    fuge
    -0.55
     tvb
    -0.55
    POSITIVE LOGITS
    الإنجليزية
    0.65
     WebApplication
    0.63
    KommentareTeilen
    0.61
    ../../../
    0.57
     nomme
    0.57
     oeufs
    0.57
    ../../
    0.56
    Демографія
    0.54
    (&:
    0.53
    ----</
    0.52
    Activations Density 0.229%

    No Known Activations