© 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. 6259
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon

    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
    1705
    +0.15
    0.6%
    1870
    +0.15
    0.6%
    82
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.15
    0.04
    82
    +0.15
    0.03
    1103
    +0.14
    0.03
    Negative Logits
     Vorm
    -0.65
     faggot
    -0.60
     gliss
    -0.57
     gabri
    -0.57
     drago
    -0.56
     pessi
    -0.54
     disgra
    -0.53
     bayern
    -0.53
     drey
    -0.53
     uniti
    -0.53
    POSITIVE LOGITS
     tech
    1.25
     Tech
    1.20
    Tech
    1.11
    tech
    1.07
     technical
    1.04
     Technical
    1.00
    Technical
    1.00
     TECH
    1.00
    technical
    0.98
     techs
    0.93
    Activations Density 0.061%

    No Known Activations