© 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. 6282
    Prev
    Next
    INDEX
    Explanations

    terms related to management, development, and environmental factors

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

    followed by "ment" or "ments"

    np_acts-logits-general · gemini-2.0-flash

    words ending in -ment

    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
     nakalista
    -0.63
     Wikispecies
    -0.58
     HasFactory
    -0.55
     Noi
    -0.55
    alba
    -0.55
    DotNetBar
    -0.55
    Tikang
    -0.53
     yii
    -0.53
    esgue
    -0.52
    psia
    -0.52
    POSITIVE LOGITS
    ment
    1.79
    MENT
    1.62
    ments
    1.62
     ment
    1.38
    mento
    1.36
    Ment
    1.34
    ement
    1.33
    menta
    1.29
    men
    1.27
    MENTS
    1.24
    Activations Density 0.311%

    No Known Activations