© 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. 15215
    Prev
    Next
    INDEX
    Explanations

    examples of financial and investment scenarios

    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
    2034
    +0.14
    0.5%
    2019
    +0.12
    0.4%
    50
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1406
    +0.14
    0.03
    89
    +0.12
    0.02
    62
    +0.11
    0.02
    Negative Logits
     applau
    -0.75
     sopr
    -0.74
     incess
    -0.73
     batte
    -0.73
     nutr
    -0.72
     tass
    -0.72
    postolic
    -0.68
     sappi
    -0.68
     intit
    -0.67
     espé
    -0.67
    POSITIVE LOGITS
     apprehen
    0.68
     vainly
    0.66
     impelled
    0.66
     unspeak
    0.60
     supposing
    0.60
     murmuring
    0.60
     gaily
    0.59
     ineffec
    0.58
     assailed
    0.57
     sighing
    0.57
    Activations Density 0.109%

    No Known Activations