© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12591
    Prev
    Next
    INDEX
    Explanations

    the word "More" and its variations, suggesting a focus on increasing quantities or additional information

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

    "More" followed by comparative words

    np_acts-logits-general · gemini-2.0-flash

    more than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    innerText
    -0.41
    <?=
    -0.39
     Deutschlands
    -0.38
    BankAccount
    -0.38
    日
    -0.37
    InnerText
    -0.37
    enderror
    -0.35
    GLOBALS
    -0.35
    annel
    -0.35
     closest
    -0.35
    POSITIVE LOGITS
     than
    1.28
     THAN
    1.01
    Than
    0.94
     niż
    0.90
    than
    0.85
     Than
    0.81
    THAN
    0.75
    Tikang
    0.68
     než
    0.67
     snippetHide
    0.66
    Activations Density 0.166%

    No Known Activations