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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 9713
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to "bit" in various technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.06
     houſe
    -1.04
     pleaſure
    -0.98
     Reſ
    -0.96
    hematical
    -0.96
    efined
    -0.95
     themſelves
    -0.95
     photolibrary
    -0.94
    (;;)
    -0.93
     FFFF
    -0.92
    POSITIVE LOGITS
     BIT
    1.50
    bit
    1.48
     Bit
    1.45
     bit
    1.39
    Bit
    1.39
     Bits
    1.36
     bits
    1.34
    Bits
    1.31
    BIT
    1.27
    bits
    1.10
    Activations Density 0.102%

    No Known Activations