© 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. 20-GEMMASCOPE-RES-16K
    11. 15465
    Prev
    Next
    INDEX
    Explanations

    references to modifications or updates made in documents or studies

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

    edits or revisions

    np_acts-logits-general · gemini-2.0-flash

    changes and modifications

    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
    helial
    -0.53
     réguli
    -0.52
    bable
    -0.48
    apunov
    -0.45
     Geraadpleegd
    -0.45
     AssemblyCulture
    -0.45
    municipi
    -0.45
    InputBorder
    -0.43
    hibli
    -0.42
     facie
    -0.41
    POSITIVE LOGITS
     modifications
    2.33
     modification
    2.21
     modified
    2.16
     Modifications
    2.07
     modify
    1.95
    Modifications
    1.89
     Modification
    1.87
    modific
    1.86
     tweaks
    1.85
     modific
    1.85
    Activations Density 1.362%

    No Known Activations