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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11075
    Prev
    Next
    INDEX
    Explanations

    terms related to technical documents and project explanations, primarily focusing on white papers

    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
    1150
    +0.18
    0.5%
    872
    +0.11
    0.3%
    1493
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1493
    +0.18
    0.04
    576
    +0.11
    0.06
    1150
    +0.11
    0.03
    Negative Logits
     swarovski
    -1.47
     hairc
    -1.44
     fta
    -1.43
     matel
    -1.41
     snoopy
    -1.39
     increa
    -1.39
     milf
    -1.36
     fte
    -1.34
     ftu
    -1.32
     broderie
    -1.31
    POSITIVE LOGITS
    document
    0.78
     document
    0.76
     containing
    0.69
     downloaded
    0.68
     printed
    0.67
     documents
    0.66
    PDF
    0.66
     published
    0.66
     written
    0.66
     sent
    0.65
    Activations Density 0.813%

    No Known Activations