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. 12722
    Prev
    Next
    INDEX
    Explanations

    mathematical relationships and conditions involving inequalities and limits

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

    Mathematical statements with "holds"

    np_acts-logits-general · gemini-2.0-flash

    mathematical conditions hold

    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
    oredCriteria
    -0.68
    tagHelperRunner
    -0.67
     createSprite
    -0.66
     onBind
    -0.64
    __(/*!
    -0.63
    BeginContext
    -0.62
     الرياضيه
    -0.61
     getopt
    -0.58
    MLLoader
    -0.57
    ORTH
    -0.56
    POSITIVE LOGITS
     holds
    1.10
     hold
    1.03
    holds
    0.93
     Holds
    0.93
     Hold
    0.88
     implies
    0.86
     HOLD
    0.83
    hold
    0.82
     Holding
    0.82
    Holding
    0.77
    Activations Density 1.682%

    No Known Activations