Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8134
    Prev
    Next
    INDEX
    Explanations

    statistics and information related to demographic representation

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

    "family"

    np_acts-logits-general · gemini-2.0-flash

    family structure

    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
    DockStyle
    -0.43
    lewati
    -0.36
    ="@+
    -0.33
    lierten
    -0.33
    átka
    -0.33
    harusnya
    -0.32
    ∉
    -0.32
     Meteorology
    -0.32
     Posture
    -0.32
    SCRIBE
    -0.32
    POSITIVE LOGITS
     family
    1.49
     Family
    1.39
    Family
    1.33
     FAMILY
    1.30
    family
    1.30
     families
    1.23
    FAMILY
    1.20
    Families
    1.15
     Families
    1.14
     familial
    1.13
    Activations Density 0.801%

    No Known Activations