© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3975
    Prev
    Next
    INDEX
    Explanations

    mathematical or algorithmic definitions and operations

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

    Followed by "G" or "g" after "#define"

    np_acts-logits-general · gemini-2.0-flash

    #define followed by G or g

    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
     Toc
    -0.39
     NDL
    -0.38
    Pherson
    -0.37
    textBox
    -0.35
    TextBlock
    -0.35
     Aniston
    -0.35
     AttributeSet
    -0.35
     Attila
    -0.35
    setDescription
    -0.34
    stuhl
    -0.34
    POSITIVE LOGITS
     głos
    0.76
     gênero
    0.74
     G
    0.73
     Gubernur
    0.71
    OGND
    0.69
    Glucose
    0.68
    AndEndTag
    0.68
    G
    0.67
     género
    0.67
     gland
    0.66
    Activations Density 2.100%

    No Known Activations