© 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. 20-GEMMASCOPE-RES-16K
    6. 266
    Prev
    Next
    INDEX
    Explanations

    phrases related to recommendations and suggestions for decision-making

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

    preceding suggestions or considerations

    np_acts-logits-general · gemini-2.0-flash

    consider or think about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.68
     ujednoznacz
    -0.54
     noqa
    -0.54
    ipients
    -0.54
    StoryboardSegue
    -0.53
     صوتيه
    -0.52
    webElementGuid
    -0.51
     Савезне
    -0.51
    Fixes
    -0.50
    TagMode
    -0.50
    POSITIVE LOGITS
     consider
    2.34
     consideration
    2.13
    Consider
    2.13
     Consider
    2.12
    consider
    2.08
     considering
    2.05
     CONSIDER
    2.05
    CONSIDER
    1.91
     considerar
    1.90
     considers
    1.84
    Activations Density 0.315%

    No Known Activations