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. 4361
    Prev
    Next
    INDEX
    Explanations

    words associated with obtaining or pursuing something

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

    Tokens starting with "Pur"

    np_acts-logits-general · gemini-2.0-flash

    words starting with pur

    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
    afficheront
    -0.51
    agrama
    -0.51
     Kreuz
    -0.50
    WithIOException
    -0.50
     autorytatywna
    -0.50
    Билгалдахарш
    -0.49
    FieldBuilder
    -0.47
    meia
    -0.46
     HttpNotFound
    -0.46
    grads
    -0.46
    POSITIVE LOGITS
    Pur
    0.69
     Pur
    0.66
    pur
    0.62
    PURE
    0.59
    PullParser
    0.57
     Pure
    0.55
     PUR
    0.54
    وانید
    0.53
    Loire
    0.52
    Hentet
    0.52
    Activations Density 0.168%

    No Known Activations