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. 19-GEMMASCOPE-RES-16K
    6. 3116
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a clear identification of a situation, often involving the word "that" and the verb "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    so
    -0.44
     particular
    -0.44
    cor
    -0.42
    mer
    -0.40
     coi
    -0.39
    stos
    -0.39
    тивного
    -0.38
    cdnjs
    -0.38
    vensko
    -0.38
    Dire
    -0.38
    POSITIVE LOGITS
     what
    1.39
     where
    1.22
     how
    1.18
     why
    1.13
    what
    1.01
     hva
    0.94
    where
    0.93
     whats
    0.93
     whence
    0.93
     дописавши
    0.91
    Activations Density 0.166%

    No Known Activations