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. 1357
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions about images or visual representations

    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
    1392
    +0.13
    0.5%
    2011
    +0.13
    0.5%
    32
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1392
    +0.13
    0.03
    2011
    +0.13
    0.03
    812
    +0.12
    0.03
    Negative Logits
     kutumia
    -0.56
    Élet
    -0.52
    errHandler
    -0.52
    namientos
    -0.50
     kufanya
    -0.50
    Demografía
    -0.50
     maaaring
    -0.50
    VELOP
    -0.49
     tabPage
    -0.49
     maraming
    -0.48
    POSITIVE LOGITS
     picture
    1.25
     Picture
    1.16
    picture
    1.14
    Picture
    1.03
     PICTURE
    1.03
     pictures
    0.98
     pic
    0.91
     pict
    0.89
    PICTURE
    0.87
     Pictures
    0.84
    Activations Density 0.059%

    No Known Activations