© 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. 1840
    Prev
    Next
    INDEX
    Explanations

    statistics and numbers in text related to various topics

    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
    198
    +0.14
    0.4%
    776
    +0.14
    0.4%
    1253
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.14
    0.07
    143
    +0.14
    0.05
    499
    +0.12
    0.05
    Negative Logits
    <bos>
    -0.97
    <^
    -0.57
     garçons
    -0.57
     Syrie
    -0.56
    ₁(
    -0.56
     élev
    -0.56
     collègues
    -0.56
     sœurs
    -0.54
     FANDOM
    -0.52
     concetto
    -0.52
    POSITIVE LOGITS
     majority
    0.66
     territo
    0.59
     saad
    0.56
    Nearly
    0.53
     mahd
    0.53
     kela
    0.53
     akut
    0.52
     litoral
    0.51
     uhr
    0.51
    percent
    0.51
    Activations Density 0.266%

    No Known Activations