© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3182
    Prev
    Next
    INDEX
    Explanations

    statements attributed to speakers, particularly the use of the word "said"

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

    Follows a person's name who "said" something

    np_acts-logits-general · gemini-2.0-flash

    speech attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     său
    -0.62
     yetu
    -0.62
     Monfieur
    -0.58
     ourselves
    -0.56
     estekak
    -0.56
     démocr
    -0.56
     betweenstory
    -0.56
     Shakspeare
    -0.55
     brancas
    -0.55
     yourselves
    -0.55
    POSITIVE LOGITS
     although
    1.16
     while
    0.98
     it
    0.87
    although
    0.85
     the
    0.84
     there
    0.81
     if
    0.81
    while
    0.78
    :
    0.77
     Although
    0.75
    Activations Density 0.140%

    No Known Activations