© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1271
    Prev
    Next
    INDEX
    Explanations

    terms related to counting and scoring in various contexts

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

    terms related to graph theory, specifically edges and their counting in a directed graph

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

    counting or being counted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.99
     itſelf
    -0.94
     himſelf
    -0.94
     Jefus
    -0.93
     Theſe
    -0.90
    OGND
    -0.88
     themſelves
    -0.85
     Monfieur
    -0.85
     Efq
    -0.81
     raiſ
    -0.79
    POSITIVE LOGITS
     counted
    2.03
     count
    1.82
     counting
    1.78
     counts
    1.75
    counted
    1.57
    counting
    1.52
     Counting
    1.49
    count
    1.48
    Counting
    1.44
     COUNT
    1.42
    Activations Density 0.262%

    No Known Activations