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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 4462
    Prev
    Next
    INDEX
    Explanations

    references to bitmaps and bit errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagConstraints
    -0.94
    efined
    -0.93
    duled
    -0.90
     themſelves
    -0.86
    !("{}",
    -0.86
    Demikian
    -0.85
     ويكيميديا
    -0.85
     myſelf
    -0.85
     itſelf
    -0.83
    σθαι
    -0.83
    POSITIVE LOGITS
    bit
    2.46
     bit
    2.26
    Bit
    2.23
     Bit
    2.20
     BIT
    2.19
    BIT
    2.04
    Bits
    1.96
    bits
    1.92
     Bits
    1.88
     bits
    1.87
    Activations Density 0.040%

    No Known Activations