© 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. 18-GEMMASCOPE-RES-16K
    11. 8288
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize context and perspective in discussions or analyses

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

    "In" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    in the context of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.58
    styleType
    -0.54
     AssemblyVersion
    -0.54
    AndEndTag
    -0.51
     ujednoznacz
    -0.50
    IBarButtonItem
    -0.49
    getSelectedItem
    -0.48
    ReusableCell
    -0.48
    __(/*!
    -0.48
     Vorsch
    -0.47
    POSITIVE LOGITS
     context
    2.55
    context
    2.19
     Context
    2.09
     contexto
    1.97
    Context
    1.90
     CONTEXT
    1.89
     contextual
    1.83
     contexte
    1.81
     contex
    1.73
     contexts
    1.68
    Activations Density 0.287%

    No Known Activations