© 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. 4592
    Prev
    Next
    INDEX
    Explanations

    references to technological specifications and features

    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
    876
    +0.10
    0.3%
    1636
    +0.09
    0.3%
    678
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1636
    +0.10
    0.04
    1371
    +0.09
    0.06
    583
    +0.09
    0.03
    Negative Logits
     antik
    -0.71
     makro
    -0.70
     maksi
    -0.69
     kristal
    -0.68
     kompati
    -0.66
     bakteri
    -0.64
     organik
    -0.63
     alip
    -0.63
     kemer
    -0.63
    <bos>
    -0.62
    POSITIVE LOGITS
     cushi
    0.67
     disreg
    0.66
     gliss
    0.62
     automne
    0.61
     coerci
    0.59
     sintering
    0.58
     espé
    0.57
     graphi
    0.55
     hydrophilic
    0.55
     tupperware
    0.55
    Activations Density 0.711%

    No Known Activations