© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9376
    Prev
    Next
    INDEX
    Explanations

    actions and verbs related to discovery and motion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.98
     ویکی‌پدیا
    -0.87
    yntaxException
    -0.80
     betweenstory
    -0.76
    Geplaatst
    -0.76
    UnitTesting
    -0.74
    حياتها
    -0.69
    انجليز
    -0.68
    حياته
    -0.66
    Ɓ
    -0.64
    POSITIVE LOGITS
     grosso
    0.48
     it
    0.44
     the
    0.43
    relevant
    0.40
     harten
    0.39
    else
    0.39
    active
    0.38
     Saras
    0.38
     relevant
    0.36
    nor
    0.36
    Activations Density 0.056%

    No Known Activations