© 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. 11412
    Prev
    Next
    INDEX
    Explanations

    information related to investigations and leads in legal or criminal contexts

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

    Tokens preceding "leading" or "lead"

    np_acts-logits-general · gemini-2.0-flash

    leads to outcomes

    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
     Италијани
    -0.60
    Unmarshaller
    -0.57
    AutoresizingMask
    -0.56
    kháu
    -0.51
    IBarButtonItem
    -0.49
    laquo
    -0.48
    windowFixed
    -0.46
    viewDidLoad
    -0.45
     onSave
    -0.44
    ngdoc
    -0.44
    POSITIVE LOGITS
     leading
    3.22
     lead
    2.91
    leading
    2.89
     Leading
    2.81
    Leading
    2.73
     leads
    2.64
    lead
    2.56
     Lead
    2.39
    Lead
    2.39
     Leads
    2.38
    Activations Density 0.687%

    No Known Activations