© 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. 12041
    Prev
    Next
    INDEX
    Explanations

    information related to arrests, charges, and legal proceedings

    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
    453
    +0.11
    0.3%
    946
    +0.08
    0.2%
    1466
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1466
    +0.11
    0.03
    1915
    +0.08
    0.03
    970
    +0.08
    0.03
    Negative Logits
     pamph
    -1.02
     effe
    -0.96
     impractica
    -0.95
     ruine
    -0.95
     embodi
    -0.94
     Mlle
    -0.93
     fluo
    -0.91
     Messieurs
    -0.91
     jacques
    -0.91
     indestru
    -0.91
    POSITIVE LOGITS
     bail
    0.79
     bond
    0.73
     bonds
    0.68
    bond
    0.62
    TagMode
    0.61
    SharedCtor
    0.58
    Personensuche
    0.58
    StructEnd
    0.57
    AddHtmlAttribute
    0.57
     Bond
    0.57
    Activations Density 0.110%

    No Known Activations