© 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. 4337
    Prev
    Next
    INDEX
    Explanations

    HTML and programming code snippets

    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
    228
    +0.13
    0.5%
    303
    +0.12
    0.5%
    1296
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.13
    0.09
    663
    +0.12
    0.07
    228
    +0.12
    0.08
    Negative Logits
     Să
    -0.62
     bénéfice
    -0.60
     mécanisme
    -0.59
     fameux
    -0.56
     affirmé
    -0.55
     souligné
    -0.54
     doté
    -0.53
     Secrétaire
    -0.53
     consommate
    -0.53
     soigneusement
    -0.53
    POSITIVE LOGITS
    =”
    0.78
    “
    0.76
    =“
    0.74
    =’
    0.73
    (“
    0.73
     “
    0.73
    ”
    0.69
    (‘
    0.69
    ‘
    0.68
    …”
    0.67
    Activations Density 0.608%

    No Known Activations