© 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. 12534
    Prev
    Next
    INDEX
    Explanations

    references to different parts or locations

    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
    812
    +0.09
    0.3%
    856
    +0.08
    0.2%
    878
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.09
    0.04
    812
    +0.08
    0.03
    1036
    +0.08
    0.01
    Negative Logits
     felipe
    -0.79
     alberto
    -0.77
     faccio
    -0.77
     sergio
    -0.76
     imparare
    -0.75
     javier
    -0.75
     vorrei
    -0.75
     succede
    -0.74
     trovo
    -0.74
     roberto
    -0.72
    POSITIVE LOGITS
     areas
    0.73
    ValueStyle
    0.67
    areas
    0.67
     regions
    0.65
     Areas
    0.65
    parts
    0.61
    richTextPanel
    0.60
     parts
    0.59
    Areas
    0.59
     تضيفلها
    0.56
    Activations Density 0.225%

    No Known Activations