© 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. 6135
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental or ecological conditions

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

    Non-English text and symbols

    np_acts-logits-general · gemini-2.0-flash

    HTML tags and links

    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
    iem
    -0.58
    GIVEREF
    -0.54
    nem
    -0.52
    vem
    -0.52
     flamme
    -0.48
     تضيفلها
    -0.47
    GENE
    -0.46
    inem
    -0.46
     these
    -0.46
    dem
    -0.46
    POSITIVE LOGITS
     للاسماء
    0.79
     Normdatei
    0.69
    ArrowToggle
    0.68
    بوابة
    0.67
    enterOuterAlt
    0.66
     '\\;'
    0.64
    RenderAtEndOf
    0.63
    DebuggerNonUser
    0.63
    featureID
    0.63
    Erreferentziak
    0.63
    Activations Density 0.112%

    No Known Activations