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. 2406
    Prev
    Next
    INDEX
    Explanations

    terminology related to standing or positioning, emphasizing support or presence

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

    "Stand" or "standing" followed by a prepositional phrase

    np_acts-logits-general · gemini-2.0-flash

    stand out or stand by

    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
    writeFieldEnd
    -0.67
    ----</
    -0.60
    jago
    -0.59
     Haupts
    -0.58
     calendriers
    -0.54
    anglès
    -0.54
     douceur
    -0.54
    PyTuple
    -0.52
    ritus
    -0.52
    InteropServices
    -0.52
    POSITIVE LOGITS
     tall
    1.11
     firm
    0.96
     tallest
    0.87
    tall
    0.87
     taller
    0.84
     Tall
    0.80
    Tall
    0.80
     stand
    0.77
     TALL
    0.73
     guard
    0.72
    Activations Density 0.053%

    No Known Activations