© 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. 3855
    Prev
    Next
    INDEX
    Explanations

    mentions of family lineage and historical context

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

    "family" or family relationships

    np_acts-logits-general · gemini-2.0-flash

    family relationships and lineage

    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
    DidLoad
    -0.40
    ToUse
    -0.36
    InSeconds
    -0.33
     Bress
    -0.33
    Vorlage
    -0.33
    Mitarbeiter
    -0.33
     Tis
    -0.33
    OrderID
    -0.32
    ItemInfo
    -0.32
     BOS
    -0.31
    POSITIVE LOGITS
     family
    1.73
    family
    1.59
     FAMILY
    1.41
     família
    1.35
    Family
    1.34
     keluarga
    1.31
    FAMILY
    1.30
     familia
    1.29
     famiglia
    1.28
     famille
    1.27
    Activations Density 0.420%

    No Known Activations