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. 15518
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific methods and materials

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

    within parentheses

    np_acts-logits-general · gemini-2.0-flash

    words starting with O

    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
     صوتيه
    -0.49
    Subviews
    -0.39
    ΗΣ
    -0.37
    ITUD
    -0.36
    ätä
    -0.36
    ěry
    -0.36
     Lewandowski
    -0.36
    tikus
    -0.35
    Ậ
    -0.35
    յու
    -0.35
    POSITIVE LOGITS
     OC
    1.48
     OA
    1.45
     OB
    1.42
     OM
    1.40
     OI
    1.40
     OCS
    1.38
     OL
    1.36
     OV
    1.34
     OT
    1.33
     OW
    1.32
    Activations Density 1.095%

    No Known Activations