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. 16-GEMMASCOPE-RES-16K
    6. 1630
    Prev
    Next
    INDEX
    Explanations

    phrases indicating association or collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preposition "with" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    an accompanying detail

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    +#+
    -0.61
    DataContract
    -0.61
    toMatchSnapshot
    -0.56
    way
    -0.55
    troppo
    -0.54
    vece
    -0.54
    Permalink
    -0.52
     Viper
    -0.49
    avance
    -0.48
    انتهای
    -0.48
    POSITIVE LOGITS
    setVerticalGroup
    0.85
     emphasis
    0.76
     estimés
    0.71
    emphasis
    0.67
     no
    0.66
     notable
    0.63
     daarbij
    0.58
    complexContent
    0.58
     שוליים
    0.58
    MigrationBuilder
    0.57
    Activations Density 0.197%

    No Known Activations