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. 13960
    Prev
    Next
    INDEX
    Explanations

    occurrences of the string "Gar" in various contexts

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

    starting with "Gar" or "gar"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Gar

    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
     nakalista
    -0.64
    IntoConstraints
    -0.58
     credit
    -0.56
     blow
    -0.53
     wave
    -0.51
    χρι
    -0.48
    formKey
    -0.47
     Executive
    -0.47
    RESUMO
    -0.46
     recently
    -0.46
    POSITIVE LOGITS
    JspWriter
    0.66
    protoimpl
    0.64
     propOrder
    0.63
    RegressionTest
    0.63
     gar
    0.58
     jScrollPane
    0.56
     Gar
    0.56
    setVerticalGroup
    0.55
     jLabel
    0.54
     चीज़ों
    0.53
    Activations Density 0.136%

    No Known Activations