© 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. 10691
    Prev
    Next
    INDEX
    Explanations

    references to wetness or wet conditions

    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
    347
    +0.15
    0.5%
    1895
    +0.12
    0.4%
    976
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.15
    0.02
    976
    +0.12
    0.02
    1895
    +0.10
    0.02
    Negative Logits
     Litu
    -0.55
     vermel
    -0.52
     palav
    -0.51
     Erben
    -0.48
     parlamento
    -0.47
     taba
    -0.47
     himo
    -0.47
     Schilder
    -0.45
    awtextra
    -0.45
     bú
    -0.45
    POSITIVE LOGITS
     wet
    1.32
    wet
    1.15
     Wet
    1.14
    Wet
    1.11
     WET
    1.03
    WET
    0.93
     wetter
    0.89
     moist
    0.87
     damp
    0.83
     moisture
    0.82
    Activations Density 0.094%

    No Known Activations