© 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. 2243
    Prev
    Next
    INDEX
    Explanations

    organizations, institutions, and associations

    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
    453
    +0.14
    0.4%
    1343
    +0.12
    0.3%
    605
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    809
    +0.14
    0.04
    718
    +0.12
    0.03
    227
    +0.11
    0.04
    Negative Logits
    <bos>
    -1.28
     chodzi
    -0.65
     wcześniej
    -0.60
     pomy
    -0.59
     wiem
    -0.58
     dokładnie
    -0.57
     tubules
    -0.57
     tutaj
    -0.56
     epithe
    -0.56
     naprawdę
    -0.56
    POSITIVE LOGITS
     perpé
    1.34
     renou
    1.33
     Lég
    1.25
     Sén
    1.25
     Chapitre
    1.22
     siff
    1.19
     ché
    1.19
     franz
    1.18
     monast
    1.17
     lele
    1.17
    Activations Density 0.159%

    No Known Activations