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. 4266
    Prev
    Next
    INDEX
    Explanations

    terms related to geometric properties or calculations

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

    Mathematical or chemical formulas/notations

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation indicators

    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
    संद
    -0.47
     subject
    -0.46
    Subject
    -0.46
    zahl
    -0.46
     gustado
    -0.45
    rógeno
    -0.45
    lendir
    -0.43
    راءة
    -0.43
    buzo
    -0.43
     reds
    -0.43
    POSITIVE LOGITS
    mybatisplus
    0.74
     فريبيس
    0.68
    MessageOf
    0.64
    InjectAttribute
    0.64
    expandindo
    0.58
    DockStyle
    0.57
     handleMessage
    0.56
     tam
    0.55
    ModelSerializer
    0.54
    رشف
    0.54
    Activations Density 0.062%

    No Known Activations