© 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. 8132
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with religious preaching and explicit content

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

    ending in "y", "ier", "ily", "ish", "punch", or "ogenic"

    np_acts-logits-general · gemini-2.0-flash

    adjectives formed from nouns

    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
    GenerationType
    -0.79
     AssemblyCompany
    -0.77
     مشين
    -0.73
    posedge
    -0.69
    yntaxException
    -0.65
     Réponses
    -0.62
    SourceChecksum
    -0.60
     propOrder
    -0.59
    WebElementEntity
    -0.59
    JspWriter
    -0.58
    POSITIVE LOGITS
    y
    1.51
    iness
    1.42
    ier
    1.20
    ty
    1.18
    ily
    1.11
    iest
    1.10
    yness
    1.02
    zy
    0.98
    sy
    0.98
    gy
    0.97
    Activations Density 0.189%

    No Known Activations