© 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. 6971
    Prev
    Next
    INDEX
    Explanations

    expressions related to construction projects or renovations

    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
    1013
    +0.19
    0.6%
    1120
    +0.14
    0.4%
    1385
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.19
    0.07
    678
    +0.14
    0.05
    1013
    +0.14
    0.05
    Negative Logits
     kade
    -0.84
     hant
    -0.83
     boks
    -0.83
     krab
    -0.83
     kaos
    -0.83
     hek
    -0.80
     spont
    -0.80
     maska
    -0.80
     etui
    -0.78
     panik
    -0.78
    POSITIVE LOGITS
     Gorb
    0.74
     impractica
    0.70
     unlaw
    0.68
     McLaugh
    0.68
     pamph
    0.67
     Dissent
    0.66
     Rodrig
    0.66
     building
    0.65
     edifice
    0.65
     Bartholo
    0.64
    Activations Density 0.427%

    No Known Activations