© 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. 6800
    Prev
    Next
    INDEX
    Explanations

    references to academic publications and historical analysis

    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
    906
    +0.12
    0.4%
    924
    +0.11
    0.3%
    1699
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.12
    0.06
    924
    +0.11
    0.06
    1774
    +0.10
    0.03
    Negative Logits
    Ży
    -0.77
    Wię
    -0.73
    Dlaczego
    -0.72
    Przed
    -0.70
    Przyp
    -0.70
    Kiedy
    -0.69
    Uwaga
    -0.69
    Gdzie
    -0.67
    muito
    -0.66
    Witaj
    -0.66
    POSITIVE LOGITS
     appui
    1.07
     vété
    1.00
     confé
    0.99
     attemp
    0.97
     vieill
    0.96
     éto
    0.96
     clô
    0.95
     exemplaire
    0.95
     wikihow
    0.95
     purcha
    0.95
    Activations Density 0.386%

    No Known Activations