© 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. 6873
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations and events

    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
    50
    +0.25
    0.9%
    1741
    +0.24
    0.9%
    2019
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.25
    0.05
    16
    +0.24
    0.07
    1771
    +0.18
    0.04
    Negative Logits
     oeil
    -0.96
     yoda
    -0.95
     dîner
    -0.93
     bâton
    -0.93
     gardien
    -0.90
     noël
    -0.89
     vété
    -0.86
     trouva
    -0.86
     madonna
    -0.85
     ritratto
    -0.85
    POSITIVE LOGITS
     majority
    0.71
     fact
    0.70
     overall
    0.67
     vast
    0.67
     biggest
    0.66
     latter
    0.66
     lack
    0.64
     ultimate
    0.63
     underlying
    0.63
     same
    0.63
    Activations Density 0.242%

    No Known Activations