© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12567
    Prev
    Next
    INDEX
    Explanations

    terms related to web development and technology concepts

    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
    872
    +0.12
    0.3%
    651
    +0.10
    0.3%
    394
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.04
    394
    +0.10
    0.05
    1383
    +0.09
    0.04
    Negative Logits
    पया
    -0.78
    ffilm
    -0.70
     vinil
    -0.70
     Himo
    -0.69
    GEBURTSDATUM
    -0.69
     indisponible
    -0.68
     €€
    -0.67
     himo
    -0.67
    WithIOException
    -0.66
     patata
    -0.66
    POSITIVE LOGITS
     refers
    1.00
     consists
    0.96
     is
    0.85
     means
    0.85
     comprises
    0.85
     encompasses
    0.81
     represents
    0.81
     signifies
    0.80
     involves
    0.79
     fta
    0.78
    Activations Density 0.411%

    No Known Activations