© 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. 14724
    Prev
    Next
    INDEX
    Explanations

    numerical measurements such as dimensions and sizes

    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
    1385
    +0.17
    0.5%
    906
    +0.14
    0.4%
    876
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1780
    +0.17
    0.04
    609
    +0.14
    0.04
    1352
    +0.11
    0.05
    Negative Logits
    ItemBackground
    -0.62
     neoliber
    -0.59
     smtplib
    -0.57
    oredCriteria
    -0.56
    ThroughAttribute
    -0.55
     Италијани
    -0.54
     aislada
    -0.52
    encodeWith
    -0.51
     Theolog
    -0.51
    żo
    -0.51
    POSITIVE LOGITS
     ananas
    0.93
     habet
    0.85
     eorum
    0.82
     ejus
    0.78
     veau
    0.75
     Methanol
    0.74
     balkon
    0.74
     Reagents
    0.74
     meis
    0.73
     velours
    0.73
    Activations Density 0.274%

    No Known Activations