© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12595
    Prev
    Next
    INDEX
    Explanations

    references to mainstream media or mainstream publications

    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
    1870
    +0.14
    0.5%
    200
    +0.11
    0.4%
    757
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.14
    0.01
    198
    +0.11
    0.02
    900
    +0.09
    0.02
    Negative Logits
     intersper
    -0.52
     vété
    -0.50
    iuo
    -0.49
     sûrement
    -0.48
     possu
    -0.48
    Molto
    -0.48
     yel
    -0.46
     récon
    -0.46
    schwar
    -0.46
     joli
    -0.45
    POSITIVE LOGITS
     mainstream
    1.14
     CiNii
    0.63
     barbacoa
    0.60
    omenclature
    0.59
    estream
    0.58
    Autoritní
    0.57
     Darío
    0.56
     Joaquín
    0.56
    ficit
    0.55
    主流
    0.54
    Activations Density 0.086%

    No Known Activations