© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    statements from authorities or officials in press releases

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

    Follows "a" (or other tokens) in press releases

    np_acts-logits-general · gemini-2.0-flash

    statement following "a"

    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
     '\\;'
    -0.93
    RenderAtEndOf
    -0.70
     kaarangay
    -0.69
    expandindo
    -0.69
    FormTagHelper
    -0.65
     Lijst
    -0.64
    Istorija
    -0.61
    writeFieldEnd
    -0.61
    ließlich
    -0.60
    الإنجليزية
    -0.59
    POSITIVE LOGITS
     press
    1.19
     statement
    1.15
     release
    1.04
     comunicado
    1.01
     пресс
    0.98
     Release
    0.92
    statement
    0.92
     Press
    0.90
     description
    0.90
     Statement
    0.90
    Activations Density 0.115%

    No Known Activations