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. 2-GEMMASCOPE-RES-16K
    6. 15447
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names associated with people and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tryk
    -0.47
    ucco
    -0.45
    {~
    -0.45
    dropna
    -0.45
    كرة
    -0.45
    ネート
    -0.43
     hl
    -0.43
    事前
    -0.42
    ânea
    -0.42
     cùng
    -0.41
    POSITIVE LOGITS
    GraphicsUnit
    1.08
     BoxFit
    0.83
     مرئيه
    0.82
    \{\\
    0.81
    expandindo
    0.79
     المعيارى
    0.75
    ScopeManager
    0.74
     TextInputType
    0.73
    RunWith
    0.72
     BorderRadius
    0.72
    Activations Density 3.341%

    No Known Activations