© 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 EvalsExportsinterp-engineNEWAPI 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. 16309
    Prev
    Next
    INDEX
    Explanations

    keywords related to computer programming languages, code optimization, and technology advances

    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
    1194
    +0.10
    0.3%
    674
    +0.10
    0.3%
    755
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.10
    0.04
    588
    +0.10
    0.04
    232
    +0.08
    0.04
    Negative Logits
     attemp
    -1.24
     alre
    -1.22
     inev
    -1.22
     increa
    -1.16
     impra
    -1.15
     emphat
    -1.11
     secon
    -1.10
     encomp
    -1.10
     aen
    -1.09
     fta
    -1.08
    POSITIVE LOGITS
    <bos>
    1.10
     better
    0.92
     easier
    0.90
     worse
    0.82
     more
    0.82
     stronger
    0.82
     harder
    0.81
     greater
    0.78
     faster
    0.78
     bigger
    0.75
    Activations Density 0.139%

    No Known Activations