© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4187
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating "more than" or comparisons

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

    the word "than"

    np_acts-logits-general · gemini-2.0-flash

    than comparative phrases

    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
    tagHelperRunner
    -0.52
    PerformLayout
    -0.46
    UnusedPrivate
    -0.44
    //
    -0.40
    +#+#
    -0.40
    postIndex
    -0.38
    glfw
    -0.38
    WriteBarrier
    -0.38
    Diweddarwch
    -0.37
     ujednoznacz
    -0.36
    POSITIVE LOGITS
     THAN
    0.82
     than
    0.71
    THAN
    0.69
     Than
    0.69
    than
    0.69
    Than
    0.68
     ніж
    0.59
     än
    0.54
     zwykle
    0.53
    olverine
    0.53
    Activations Density 0.143%

    No Known Activations