© 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. 8939
    Prev
    Next
    INDEX
    Explanations

    verbs related to the action of pulling

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

    "pull" or its variations

    np_acts-logits-general · gemini-2.0-flash

    pull and pull together

    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
    Personensuche
    -0.97
    XmlAccessorType
    -0.77
    XmlAccessType
    -0.75
     BorderRadius
    -0.74
     onOptions
    -0.73
    esModule
    -0.66
    MessageOf
    -0.65
    Personendaten
    -0.65
    AccessorTable
    -0.64
    DockStyle
    -0.64
    POSITIVE LOGITS
     pull
    1.56
    pull
    1.48
     pulls
    1.45
     pulled
    1.43
     Pull
    1.43
     pulling
    1.42
     PULL
    1.39
    Pull
    1.39
     Pulling
    1.34
    PULL
    1.27
    Activations Density 0.056%

    No Known Activations