© 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. 7307
    Prev
    Next
    INDEX
    Explanations

    words associated with technical platforms and services

    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
    1403
    +0.12
    0.3%
    198
    +0.10
    0.3%
    1385
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.12
    0.03
    1003
    +0.10
    0.01
    678
    +0.09
    0.03
    Negative Logits
     fuper
    -0.78
     caufe
    -0.72
     difp
    -0.71
     nuage
    -0.71
     reafon
    -0.70
     defire
    -0.68
     bourg
    -0.68
     whofe
    -0.67
     bénéfice
    -0.67
     juft
    -0.65
    POSITIVE LOGITS
     tyn
    0.77
     lapto
    0.77
     ads
    0.72
     advertising
    0.68
     advertisers
    0.67
     kask
    0.66
    vertisers
    0.65
     boks
    0.64
     tages
    0.63
     kuns
    0.62
    Activations Density 0.191%

    No Known Activations