© 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. 0-GEMMASCOPE-RES-16K
    6. 7279
    Prev
    Next
    INDEX
    Explanations

    the word "indeed" and its variations indicating affirmation or confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.58
    polite
    -0.58
    出版年
    -0.57
     polite
    -0.57
     Busse
    -0.53
    RTLI
    -0.53
    mappedBy
    -0.52
     Lue
    -0.52
     Letter
    -0.51
    ništvo
    -0.51
    POSITIVE LOGITS
     indeed
    0.54
     Савезне
    0.48
     Infórmanos
    0.48
     nemlig
    0.46
     bowiem
    0.46
     Verhält
    0.44
    indeed
    0.42
     infatti
    0.40
     totiž
    0.40
     avoient
    0.38
    Activations Density 0.186%

    No Known Activations