© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 12354
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to financial data analysis

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

    Superscripted numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    bioleaf biotech

    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
    ՚
    -0.55
     لينك
    -0.53
    tieth
    -0.53
    ,…
    -0.50
     native
    -0.48
     […]
    -0.47
    Naissance
    -0.46
    …,
    -0.46
     Wint
    -0.46
    </h1>
    -0.45
    POSITIVE LOGITS
    __":
    0.68
     createState
    0.67
    IVEREF
    0.60
    GIVEREF
    0.59
     дописавши
    0.57
     ricorda
    0.57
    AndroidJUnit
    0.55
    MemoryWarning
    0.55
    glEnd
    0.54
    DECREF
    0.54
    Activations Density 0.036%

    No Known Activations