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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53501
    Prev
    Next
    INDEX
    Explanations

    the presence of function calls in code

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

    parentheses and semicolons

    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
     صوتيه
    -0.81
    mtrl
    -0.76
    RetentionPolicy
    -0.71
    sizeCache
    -0.69
    BagConstraints
    -0.69
    rungsseite
    -0.66
     arşivlendi
    -0.66
     kasarigan
    -0.65
    :✨
    -0.65
    __":
    
    -0.65
    POSITIVE LOGITS
     poffible
    0.62
     þat
    0.50
     ſet
    0.49
     obſ
    0.49
     paſſ
    0.48
     Secondly
    0.47
     ſche
    0.47
     Reſ
    0.47
     ſtre
    0.47
    さてさて
    0.47
    Activations Density 0.504%

    No Known Activations