© 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. 3592
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate numerical data or specific references related to quantity

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

    Followed by "case" or "Case"

    np_acts-logits-general · gemini-2.0-flash

    cases

    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
    tagHelperRunner
    -0.87
    SourceChecksum
    -0.75
    ScopeManager
    -0.66
    mybatisplus
    -0.62
     ComVisible
    -0.62
    PreInfinity
    -0.61
    LookAnd
    -0.60
    OGND
    -0.60
    riwal
    -0.59
    DockStyle
    -0.59
    POSITIVE LOGITS
     case
    4.71
    case
    3.98
    Case
    3.71
     Case
    3.69
     cases
    3.40
     caso
    3.23
     CASE
    3.20
    CASE
    3.16
     Cases
    2.88
    cases
    2.82
    Activations Density 0.944%

    No Known Activations