© 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. 14774
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "so much" is used

    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
    131
    +0.12
    0.4%
    1350
    +0.12
    0.4%
    1983
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    866
    +0.12
    0.03
    131
    +0.12
    0.03
    650
    +0.12
    0.03
    Negative Logits
    Transcrip
    -0.54
    İstinadlar
    -0.44
     Bever
    -0.43
    ----</
    -0.43
    ACKNOWLEDGEMENTS
    -0.43
     Holloway
    -0.43
    Jus
    -0.42
    Đăng
    -0.42
    cửa
    -0.42
    Cabe
    -0.42
    POSITIVE LOGITS
     peugeot
    0.63
    fordable
    0.63
     fatis
    0.62
     flyknit
    0.61
     asics
    0.61
     permu
    0.61
     melat
    0.61
     fup
    0.60
     ufe
    0.60
     sentra
    0.59
    Activations Density 0.113%

    No Known Activations