© 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. 4704
    Prev
    Next
    INDEX
    Explanations

    information about geographical locations and measurements

    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
    1741
    +0.13
    0.4%
    2015
    +0.12
    0.4%
    453
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.13
    0.06
    453
    +0.12
    0.06
    1804
    +0.11
    0.05
    Negative Logits
     unspeak
    -1.36
    <bos>
    -1.29
     philosophic
    -1.15
     liberality
    -1.12
     impelled
    -1.09
     tolerably
    -1.08
     vainly
    -1.07
     unwarran
    -1.07
     endeavouring
    -1.07
     poetical
    -1.06
    POSITIVE LOGITS
     elek
    1.90
     utop
    1.89
     marte
    1.84
     hek
    1.81
     kask
    1.80
     alkoh
    1.79
     moza
    1.79
     balon
    1.78
     makro
    1.78
     kram
    1.77
    Activations Density 0.389%

    No Known Activations