© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2133
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and numbers

    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
    1757
    +0.14
    0.6%
    101
    +0.14
    0.6%
    645
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1472
    +0.14
    0.06
    1271
    +0.14
    0.07
    645
    +0.14
    0.07
    Negative Logits
    Dziękuję
    -0.66
     caprice
    -0.62
     depic
    -0.60
     berea
    -0.57
     domani
    -0.57
     tupperware
    -0.57
     hdi
    -0.57
     impractica
    -0.57
     morrow
    -0.56
     indestru
    -0.56
    POSITIVE LOGITS
    4
    0.91
     Thursday
    0.69
     IV
    0.69
    Thursday
    0.66
    IV
    0.65
     Fourth
    0.65
    four
    0.64
     cuarta
    0.62
    ৪
    0.62
    fourth
    0.60
    Activations Density 0.284%

    No Known Activations