© 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 EvalsExportsinterp-engineNEWAPI 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. 15230
    Prev
    Next
    INDEX
    Explanations

    phrases related to excerpts, screenshots, and reports

    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
    +0.11
    0.4%
    690
    +0.11
    0.3%
    122
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.11
    0.03
    1467
    +0.11
    0.02
    1305
    +0.10
    0.02
    Negative Logits
     shutterstock
    -0.90
     ordina
    -0.87
     pixabay
    -0.87
     Chá
    -0.85
    ⓧ
    -0.83
     Perci
    -0.80
     Nö
    -0.79
     onor
    -0.79
     nomine
    -0.79
     intit
    -0.78
    POSITIVE LOGITS
     snippets
    0.78
     screenshot
    0.76
     snippet
    0.74
     screenshots
    0.71
     excerpts
    0.69
     of
    0.66
     excerpt
    0.66
    cerpts
    0.66
     snapshot
    0.64
     snapshots
    0.62
    Activations Density 0.162%

    No Known Activations