© 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. 13182
    Prev
    Next
    INDEX
    Explanations

    biology or laboratory-related procedures and 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
    453
    +0.14
    0.4%
    478
    +0.13
    0.4%
    382
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    862
    +0.14
    0.07
    478
    +0.13
    0.05
    1023
    +0.11
    0.06
    Negative Logits
     negru
    -0.85
     véhic
    -0.79
     Româ
    -0.76
     viendra
    -0.72
     sarili
    -0.70
     soigne
    -0.69
     susun
    -0.68
     panahon
    -0.68
     déchir
    -0.67
     épu
    -0.67
    POSITIVE LOGITS
     taken
    0.66
     examined
    0.62
     kept
    0.60
     placed
    0.59
     banque
    0.59
     stik
    0.59
     teken
    0.59
    ⓧ
    0.58
     considere
    0.57
    theless
    0.57
    Activations Density 0.407%

    No Known Activations