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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1072
    Prev
    Next
    INDEX
    Explanations

    instances of object instantiation and creation in programming contexts

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

    Follows "new" or detects code-related terms

    np_acts-logits-general · gemini-2.0-flash

    new object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     EconPapers
    -0.53
    ViewFeatures
    -0.52
     للاسماء
    -0.49
     antemano
    -0.49
     Taktlose
    -0.47
     jälkeen
    -0.46
     Moscú
    -0.45
     exceso
    -0.45
     reuniones
    -0.44
    ksessa
    -0.44
    POSITIVE LOGITS
     Otto
    0.48
     fant
    0.45
     autorytatywna
    0.44
     newUser
    0.44
     Jane
    0.43
     Del
    0.43
     Devil
    0.43
    InstanceOf
    0.43
     Anna
    0.43
     Dew
    0.42
    Activations Density 0.198%

    No Known Activations