Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11366
    Prev
    Next
    INDEX
    Explanations

    modal verbs and phrases expressing possibility and ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izzling
    -0.37
    ล่า
    -0.37
     Hartman
    -0.35
     Gemeins
    -0.34
    setLength
    -0.34
    relógio
    -0.34
    alaj
    -0.34
     הב
    -0.34
     its
    -0.34
    SETTING
    -0.33
    POSITIVE LOGITS
    可
    0.79
    可以
    0.70
    GEBURTSDATUM
    0.68
     ניתן
    0.67
     dapat
    0.66
     canst
    0.65
     可以
    0.64
     ممكن
    0.64
     podemos
    0.64
    можно
    0.64
    Activations Density 0.302%

    No Known Activations