© 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. 22-GEMMASCOPE-RES-16K
    11. 10636
    Prev
    Next
    INDEX
    Explanations

    HTML tags and line breaks

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

    HTML line breaks

    np_acts-logits-general · gemini-2.0-flash

    HTML line break tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    modelBuilder
    -0.97
    SBATCH
    -0.86
    Datuak
    -0.84
    ContentAsync
    -0.82
     lenker
    -0.79
    ConstraintMaker
    -0.79
    RenderAtEndOf
    -0.78
     ?>>
    -0.78
    tagHelper
    -0.78
    findpost
    -0.78
    POSITIVE LOGITS
     Br
    0.64
    br
    0.61
    Br
    0.60
    /
    0.48
     fe
    0.45
     clear
    0.45
     />
    0.44
    ty
    0.44
     br
    0.43
     Pet
    0.42
    Activations Density 0.077%

    No Known Activations