© 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. 7527
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and personal connections

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

    Possessive pronoun followed by a family member

    np_acts-logits-general · gemini-2.0-flash

    family members and relationships

    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
     완
    -0.41
    致
    -0.35
    ập
    -0.35
    CON
    -0.34
    OVERR
    -0.34
     clean
    -0.34
    seitig
    -0.34
    Soft
    -0.33
    指
    -0.33
    CUR
    -0.32
    POSITIVE LOGITS
     виправивши
    0.75
     $_"
    0.71
     wife
    0.71
     nahilalakip
    0.70
    Diweddarwch
    0.69
    LLocation
    0.68
    AnimationsModule
    0.67
     AttributeSet
    0.66
    OGND
    0.66
    lapsingToolbar
    0.65
    Activations Density 0.205%

    No Known Activations