© 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. 22-GEMMASCOPE-RES-16K
    6. 3101
    Prev
    Next
    INDEX
    Explanations

    technical aspects of graphic design tools and their functionalities

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

    GUI text editing actions

    np_acts-logits-general · gemini-2.0-flash

    select, drag, copy, paste

    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
    LookAnd
    -0.73
    gameserver
    -0.60
    uxxxx
    -0.59
     detoxification
    -0.58
     profondo
    -0.56
     noires
    -0.53
    LogFactory
    -0.53
     sportivo
    -0.52
     diversification
    -0.52
     profundas
    -0.51
    POSITIVE LOGITS
     selection
    0.91
     Selection
    0.83
     selected
    0.80
     drag
    0.78
     edit
    0.77
     Edit
    0.76
     Drag
    0.75
    selection
    0.74
     selections
    0.72
     select
    0.72
    Activations Density 0.435%

    No Known Activations