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. 7-GEMMASCOPE-RES-16K
    6. 8883
    Prev
    Next
    INDEX
    Explanations

    instances of abstract concepts and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -0.67
    RenderAtEndOf
    -0.62
    __(/*!
    -0.55
    UseVisualStyle
    -0.53
    endregion
    -0.53
    JsonInclude
    -0.51
    daß
    -0.50
    確実に
    -0.49
    QApplication
    -0.49
    guchi
    -0.48
    POSITIVE LOGITS
     abstra
    0.98
     abstrak
    0.94
     abstraction
    0.92
     abstractions
    0.89
     abstract
    0.87
     Abstra
    0.86
     vague
    0.84
     abstracta
    0.84
     abstracted
    0.83
    abstra
    0.81
    Activations Density 0.354%

    No Known Activations