© 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. 12627
    Prev
    Next
    INDEX
    Explanations

    references to "paper" in various contexts

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

    "Paper"

    np_acts-logits-general · gemini-2.0-flash

    PaperThin and paper cutting

    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
    ]--;
    -0.60
     المعيارى
    -0.59
     BoxFit
    -0.59
    DataAnnotations
    -0.58
    schild
    -0.57
    unhofer
    -0.56
    URLConnection
    -0.55
    createClass
    -0.54
    первых
    -0.54
    insen
    -0.53
    POSITIVE LOGITS
    clip
    0.80
     mache
    0.76
     mâ
    0.70
    clips
    0.68
     mills
    0.65
     towel
    0.62
     towels
    0.62
    weight
    0.61
     mill
    0.61
    mache
    0.59
    Activations Density 0.061%

    No Known Activations