© 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. 4270
    Prev
    Next
    INDEX
    Explanations

    URLs and website paths

    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
    2019
    +0.17
    0.6%
    1403
    +0.14
    0.5%
    1343
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.17
    0.03
    576
    +0.14
    0.03
    924
    +0.14
    0.03
    Negative Logits
    Dichlor
    -0.68
    bidden
    -0.63
    ]$}
    -0.59
    Trimethyl
    -0.57
     AssemblyTitle
    -0.56
    eficiente
    -0.56
    Toluene
    -0.55
    Naphthalene
    -0.55
    aimerais
    -0.55
    aurais
    -0.55
    POSITIVE LOGITS
    arture
    1.03
     practition
    0.98
    ividual
    0.97
    tificial
    0.97
     jaya
    0.93
     resear
    0.93
    anical
    0.91
    pection
    0.91
     berea
    0.91
     wherea
    0.89
    Activations Density 0.046%

    No Known Activations