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. 23-GEMMASCOPE-RES-16K
    6. 12091
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibilities and completion of construction tasks

    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
    StoryboardSegue
    -0.81
     дописавши
    -0.71
    EndInit
    -0.66
     Normdatei
    -0.60
     nahilalakip
    -0.60
     chi̍t
    -0.58
     >=",
    -0.57
    BeginInit
    -0.54
    Chham
    -0.54
     חיצוניים
    -0.54
    POSITIVE LOGITS
     LUMP
    0.65
     work
    0.56
     quantities
    0.56
     scope
    0.55
    istungen
    0.54
    Contract
    0.54
     Work
    0.54
     WORK
    0.52
    artist
    0.52
     Drawings
    0.52
    Activations Density 0.133%

    No Known Activations