© 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. 7066
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical information

    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
    +0.27
    0.9%
    1535
    +0.17
    0.5%
    872
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.27
    0.15
    1535
    +0.17
    0.13
    924
    +0.12
    0.13
    Negative Logits
    Conheça
    -0.71
    Czym
    -0.71
    Assista
    -0.67
    Composição
    -0.65
    Einen
    -0.65
    Característica
    -0.65
    Și
    -0.64
    Significado
    -0.63
    Dicas
    -0.63
    Zapraszamy
    -0.63
    POSITIVE LOGITS
     encomp
    1.04
     maneu
    1.00
     wherea
    0.99
     fta
    0.99
     fte
    0.98
     reluct
    0.97
     depic
    0.97
     uninten
    0.96
     increa
    0.96
     gmbh
    0.95
    Activations Density 1.112%

    No Known Activations