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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 5271
    Prev
    Next
    INDEX
    Explanations

    instances of the word "original" along with its associated context in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Réponses
    -0.94
    #+#
    -0.91
     <=",
    -0.85
     decoradas
    -0.81
     дописавши
    -0.76
    MeasureSpec
    -0.75
    XtraGrid
    -0.75
    🦰
    -0.73
     ***!
    -0.72
    nestjs
    -0.71
    POSITIVE LOGITS
     original
    2.14
    Original
    2.07
     ORIGINAL
    2.01
     Original
    1.98
    original
    1.89
    ORIGINAL
    1.79
     originals
    1.74
     orig
    1.68
     originale
    1.53
     Originals
    1.49
    Activations Density 0.054%

    No Known Activations