© 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. 3871
    Prev
    Next
    INDEX
    Explanations

    legal or judicial terms

    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
    1699
    +0.10
    0.3%
    304
    +0.10
    0.3%
    478
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1493
    +0.10
    0.03
    1032
    +0.10
    0.04
    1622
    +0.09
    0.03
    Negative Logits
    Galería
    -0.87
    Quién
    -0.87
    Estás
    -0.87
    Cuánt
    -0.86
    Serviço
    -0.86
    Hemos
    -0.84
    Alguna
    -0.83
    Quieres
    -0.83
    Oficina
    -0.82
    Carreira
    -0.82
    POSITIVE LOGITS
     milf
    2.52
     stockholm
    2.51
     michelin
    2.45
     affor
    2.41
     lidl
    2.41
     perfet
    2.37
     casio
    2.36
     peppa
    2.35
     secon
    2.34
     lola
    2.31
    Activations Density 0.206%

    No Known Activations