© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7378
    Prev
    Next
    INDEX
    Explanations

    method names and special keywords in a programming context

    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
    1065
    +0.20
    0.9%
    406
    +0.18
    0.8%
    479
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1065
    +0.20
    0.03
    406
    +0.18
    0.01
    981
    +0.17
    0.03
    Negative Logits
     James
    -0.49
     Kraus
    -0.48
     Amanda
    -0.48
    James
    -0.45
     Denis
    -0.45
     Markham
    -0.44
    Sultan
    -0.44
     Whiting
    -0.43
    Amanda
    -0.43
    Denis
    -0.42
    POSITIVE LOGITS
     ftu
    0.88
     fep
    0.87
     Docteur
    0.86
     poff
    0.85
     fign
    0.85
     lende
    0.84
     fta
    0.84
     fto
    0.83
     effe
    0.82
     bénéficiaire
    0.81
    Activations Density 0.205%

    No Known Activations