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. 10-GEMMASCOPE-RES-16K
    6. 15750
    Prev
    Next
    INDEX
    Explanations

    URLs and HTML elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.69
    zeera
    -0.61
    :+:
    -0.58
    duğu
    -0.56
    onnaissance
    -0.49
     ExecuteAsync
    -0.49
     ball
    -0.48
    ritsar
    -0.47
     Aptitude
    -0.47
     supri
    -0.47
    POSITIVE LOGITS
    ########.
    0.87
     ProtoMessage
    0.69
     ComVisible
    0.69
     Theſe
    0.67
    
    0.65
    TargetException
    0.64
     surla
    0.64
    存于互联网档案馆
    0.63
    \{\\
    0.63
     Baillargeon
    0.61
    Activations Density 0.066%

    No Known Activations