© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6827
    Prev
    Next
    INDEX
    Explanations

    words related to proposals or suggestions

    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
    1323
    +0.13
    0.4%
    31
    +0.12
    0.4%
    1222
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.13
    0.10
    1381
    +0.12
    0.08
    1323
    +0.12
    0.07
    Negative Logits
    θρώ
    -0.65
    devServer
    -0.61
    葩
    -0.60
    waitKey
    -0.58
     MainAxisSize
    -0.58
     itinéraire
    -0.58
    DeleteMapping
    -0.57
    PerformLayout
    -0.57
    Scénario
    -0.57
    makeText
    -0.57
    POSITIVE LOGITS
     intersper
    1.09
     maneu
    1.08
     scrat
    1.03
     guarante
    1.02
     emphat
    1.01
     canel
    0.99
     affor
    0.99
     attemp
    0.99
     secon
    0.98
     resear
    0.98
    Activations Density 0.307%

    No Known Activations