© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8949
    Prev
    Next
    INDEX
    Explanations

    questions related to identity and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.77
    出版年
    -0.71
    expandindo
    -0.70
     فريبيس
    -0.67
     Normdatei
    -0.67
    tagHelperRunner
    -0.67
     MaterialApp
    -0.66
    interopRequire
    -0.63
    RectangleBorder
    -0.59
    ScopeManager
    -0.58
    POSITIVE LOGITS
    liesslich
    0.56
    assertj
    0.55
     счёт
    0.53
    andoah
    0.52
    enced
    0.50
    stino
    0.50
    thâu
    0.49
    pearing
    0.48
    fo
    0.48
    زیک
    0.48
    Activations Density 0.312%

    No Known Activations