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. 22-GEMMASCOPE-RES-16K
    6. 8713
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and mathematical operations

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

    Preceding or containing the number zero

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code contexts with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nuss
    -0.62
    tivism
    -0.61
    あります
    -0.58
     present
    -0.58
    :],
    -0.58
    /***/
    -0.58
    classmethod
    -0.58
     walk
    -0.57
    ANGEL
    -0.56
    ]]
    
    -0.55
    POSITIVE LOGITS
    0
    1.27
    AndEndTag
    1.09
    AddTagHelper
    0.88
     Catto
    0.77
    enderror
    0.71
    +#+#
    0.71
    RegressionTest
    0.70
     utafitiHapana
    0.69
    vician
    0.69
     SCSI
    0.69
    Activations Density 1.881%

    No Known Activations