Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53080
    Prev
    Next
    INDEX
    Explanations

    terms related to current temperature and its associated data in a coding context

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

    current state or variable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kautta
    -0.58
     dolayı
    -0.52
     profundo
    -0.51
     senere
    -0.51
    irão
    -0.49
     côtés
    -0.48
     rarement
    -0.48
     médicale
    -0.47
     yder
    -0.47
    mişti
    -0.47
    POSITIVE LOGITS
    contentLoaded
    0.79
    AutoScale
    0.77
    AutoScaleMode
    0.73
    JspWriter
    0.72
    fetchone
    0.70
     propOrder
    0.70
    izational
    0.68
    </tfoot>
    0.68
     Monfieur
    0.68
    轭
    0.68
    Activations Density 0.068%

    No Known Activations