© 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. 24-GEMMASCOPE-RES-16K
    11. 8409
    Prev
    Next
    INDEX
    Explanations

    references to groups or entities and their relationships

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

    before "group" referring to size/collective

    np_acts-logits-general · gemini-2.0-flash

    group of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muualla
    -0.81
    LayoutStyle
    -0.69
    DockStyle
    -0.64
    getItemId
    -0.63
     onCreateView
    -0.62
    Areas
    -0.60
    KURZBESCHREIBUNG
    -0.58
     &___
    -0.58
    SpringBootTest
    -0.57
    velopes
    -0.56
    POSITIVE LOGITS
     group
    1.42
     crew
    1.34
     team
    1.17
     squad
    1.11
     gruppo
    1.10
     cohort
    1.06
     bunch
    1.05
     gang
    1.05
     troupe
    1.04
     contingent
    1.03
    Activations Density 0.480%

    No Known Activations