© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8076
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "whom"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.54
    InputTagHelper
    -0.52
     Theſe
    -0.49
     مرئيه
    -0.48
     becauſe
    -0.47
     Monfieur
    -0.47
     Dreams
    -0.46
     שוליים
    -0.46
    Tikang
    -0.46
    vertisement
    -0.46
    POSITIVE LOGITS
     boom
    0.63
     Boom
    0.56
     Dream
    0.53
     dream
    0.51
     closed
    0.49
    Boom
    0.49
    boom
    0.48
    Dream
    0.45
     whom
    0.44
    closed
    0.44
    Activations Density 0.060%

    No Known Activations