© 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. 4441
    Prev
    Next
    INDEX
    Explanations

    parameters and properties related to resource groups and VPN sites

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

    numbers, amounts, or quantity

    np_acts-logits-general · gemini-2.0-flash

    describing measurements and authority

    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
     Chwiliwch
    -0.66
    RegressionTest
    -0.66
    RenderAtEndOf
    -0.66
    hoeddwyd
    -0.63
    AutoScale
    -0.60
    IsContent
    -0.60
     nakalista
    -0.59
     ligiloj
    -0.57
    Климат
    -0.56
    
    -0.56
    POSITIVE LOGITS
     amount
    0.59
     represents
    0.54
     number
    0.53
     refers
    0.51
     the
    0.51
     how
    0.50
     representing
    0.48
     hoeveel
    0.46
     whether
    0.46
     pertains
    0.45
    Activations Density 0.418%

    No Known Activations