© 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. 13357
    Prev
    Next
    INDEX
    Explanations

    laws, regulations, and official procedures described either internally or externally

    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
    297
    +0.11
    0.3%
    1870
    +0.11
    0.3%
    690
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.11
    0.09
    2006
    +0.11
    0.08
    297
    +0.10
    0.07
    Negative Logits
     alkoh
    -1.11
     meis
    -1.09
     sergio
    -1.09
     kosme
    -1.09
     utop
    -1.08
     solidar
    -1.07
     socie
    -1.06
     alberto
    -1.06
     sappi
    -1.05
     spion
    -1.05
    POSITIVE LOGITS
     for
    0.62
    QUADS
    0.60
     are
    0.60
     throughout
    0.59
    pacs
    0.58
     which
    0.58
     with
    0.58
    hips
    0.57
     galore
    0.57
    contentPadding
    0.57
    Activations Density 0.703%

    No Known Activations