© 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. 23-GEMMASCOPE-RES-16K
    11. 12588
    Prev
    Next
    INDEX
    Explanations

    events or significant changes related to time transitions, particularly seasons and holidays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DataAnnotations
    -0.66
    saraba
    -0.62
    glMatrixMode
    -0.59
    InitStruct
    -0.59
     createContext
    -0.58
     ResponseEntity
    -0.58
     createSlice
    -0.55
     المعيارى
    -0.54
     steder
    -0.53
     متعلقه
    -0.53
    POSITIVE LOGITS
     approaching
    1.56
     approaches
    1.42
     APPROACH
    1.42
     approach
    1.40
     approche
    1.35
     approached
    1.25
    approach
    1.22
     Approaches
    1.20
     Approach
    1.18
    appro
    1.16
    Activations Density 0.182%

    No Known Activations