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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15772
    Prev
    Next
    INDEX
    Explanations

    information related to the size of groups, supplements, and workforce

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1042
    +0.12
    0.4%
    1385
    +0.12
    0.3%
    1381
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1675
    +0.12
    0.05
    369
    +0.12
    0.04
    1416
    +0.11
    0.03
    Negative Logits
     minValue
    -0.59
     lapin
    -0.52
     vache
    -0.51
     Vaters
    -0.48
     Sén
    -0.48
     jouet
    -0.47
     courbe
    -0.47
     comte
    -0.46
     oreille
    -0.46
     puits
    -0.45
    POSITIVE LOGITS
     sized
    0.89
     size
    0.89
    sized
    0.86
    size
    0.81
     sizes
    0.78
    Size
    0.71
     Size
    0.69
    sizes
    0.69
     SIZE
    0.68
     bigger
    0.68
    Activations Density 0.186%

    No Known Activations