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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13982
    Prev
    Next
    INDEX
    Explanations

    phrases related to political movements and ideologies

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

    Followed by quantities or superlatives

    np_acts-logits-general · gemini-2.0-flash

    strategic plans and organization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.87
     noDo
    -0.72
    PerformLayout
    -0.65
    EndInit
    -0.64
    Hochspringen
    -0.63
    aarrggbb
    -0.62
     وتسجيلات
    -0.60
    RenderAtEndOf
    -0.60
     चीज़ों
    -0.59
    awtextra
    -0.57
    POSITIVE LOGITS
     efferves
    0.60
     eminently
    0.55
     territorial
    0.52
     peri
    0.50
    entiary
    0.50
     cinemat
    0.50
     Referential
    0.49
     intermitt
    0.49
    arrant
    0.47
    entennial
    0.47
    Activations Density 0.177%

    No Known Activations