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. 4-GEMMASCOPE-RES-16K
    6. 3380
    Prev
    Next
    INDEX
    Explanations

    open parentheses in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PLO
    -0.60
     Issus
    -0.56
    存于互联网档案馆
    -0.52
     himſelf
    -0.51
     propOrder
    -0.51
     Guelph
    -0.51
    (""));
    -0.49
    :])
    -0.49
     Galveston
    -0.49
     Guadeloupe
    -0.47
    POSITIVE LOGITS
    帖最后由
    0.73
    anskje
    0.72
    OSSARY
    0.66
    Leftrightarrow
    0.65
    GRANTED
    0.63
     Plateau
    0.63
    BeginInit
    0.61
     DbSet
    0.61
    anasia
    0.60
    aroos
    0.60
    Activations Density 0.030%

    No Known Activations