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. 8098
    Prev
    Next
    INDEX
    Explanations

    specific measures and conditions related to experimental procedures

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

    time durations

    np_acts-logits-general · gemini-2.0-flash

    seconds and minutes

    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
    Personendaten
    -0.69
    PreferredItem
    -0.65
    $_['
    -0.56
     utafitiHapana
    -0.54
    GLenum
    -0.51
     pháp
    -0.50
     estekak
    -0.49
    ạnh
    -0.49
    thâu
    -0.49
    المناصب
    -0.49
    POSITIVE LOGITS
     seconds
    1.60
     sec
    1.58
    sec
    1.51
    Sec
    1.35
     Sec
    1.30
     second
    1.30
     secs
    1.29
     Seconds
    1.22
    second
    1.21
    seconds
    1.21
    Activations Density 0.416%

    No Known Activations