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. 14679
    Prev
    Next
    INDEX
    Explanations

    references to academic journals

    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
     nakalista
    -0.64
    фициальный
    -0.58
    ContentAlignment
    -0.56
    Semif
    -0.55
     Roskov
    -0.54
    overset
    -0.54
     leksikon
    -0.54
    URLException
    -0.54
    $_['
    -0.53
    CodeAnalysis
    -0.53
    POSITIVE LOGITS
    Portail
    0.87
     Journal
    0.70
    modelBuilder
    0.68
    Journal
    0.66
    PhysRev
    0.65
     BoxDecoration
    0.61
    urnal
    0.61
    ILON
    0.60
     transnational
    0.57
     journal
    0.56
    Activations Density 0.122%

    No Known Activations