© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14744
    Prev
    Next
    INDEX
    Explanations

    references to technology updates or news

    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
    776
    +0.16
    0.5%
    1271
    +0.12
    0.4%
    678
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1339
    +0.16
    0.02
    1271
    +0.12
    0.03
    776
    +0.12
    0.03
    Negative Logits
     autunno
    -0.66
    spania
    -0.57
    Voci
    -0.55
     broderie
    -0.54
     Février
    -0.50
     ""}
    -0.49
     chré
    -0.49
     rechange
    -0.49
     uovo
    -0.49
    Perché
    -0.49
    POSITIVE LOGITS
     latest
    0.95
    latest
    0.85
    Latest
    0.82
     Latest
    0.81
     LATEST
    0.69
     iteration
    0.59
     version
    0.57
     newest
    0.57
     edition
    0.57
    LATEST
    0.56
    Activations Density 0.058%

    No Known Activations