Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4545
    Prev
    Next
    INDEX
    Explanations

    temporal references related to specific events or deadlines

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

    nearness in time

    np_acts-logits-general · gemini-2.0-flash

    time approaching or ending

    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
     createContext
    -0.65
    DataAnnotations
    -0.63
     ostavi
    -0.61
    saraba
    -0.59
     ResponseEntity
    -0.56
     متعلقه
    -0.55
    CreateMap
    -0.55
    glMatrixMode
    -0.54
    σθαι
    -0.54
     snippetHide
    -0.53
    POSITIVE LOGITS
     approaching
    1.46
     APPROACH
    1.29
     approaches
    1.28
     approche
    1.21
     approach
    1.19
     Approaches
    1.10
     approached
    1.09
     Appro
    1.09
    appro
    1.08
    approach
    1.03
    Activations Density 0.201%

    No Known Activations