© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3958
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a review of evidence or knowledge about a subject

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

    Follows first-person pronouns/possessive adjectives and precedes "knowledge"

    np_acts-logits-general · gemini-2.0-flash

    to our knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atchi
    -0.39
    tură
    -0.39
     pleaſure
    -0.39
    zach
    -0.38
    TypeArgs
    -0.38
    Zá
    -0.37
    Booking
    -0.37
    anneer
    -0.37
    ASHI
    -0.37
    osuke
    -0.36
    POSITIVE LOGITS
     known
    0.94
    known
    0.84
     Known
    0.78
    Known
    0.77
     KNOWN
    0.73
     connues
    0.72
     conocidas
    0.71
     bekan
    0.70
     conocemos
    0.69
     connus
    0.68
    Activations Density 0.502%

    No Known Activations