© 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. 11825
    Prev
    Next
    INDEX
    Explanations

    arguments or positions presented by people

    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
    1392
    +0.15
    0.5%
    1872
    +0.14
    0.5%
    1527
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.15
    0.04
    1392
    +0.14
    0.05
    1527
    +0.13
    0.03
    Negative Logits
    autorisation
    -0.45
    Weir
    -0.41
    AllowUser
    -0.41
     Mit
    -0.40
    Lenny
    -0.40
    Sapp
    -0.40
    Noon
    -0.39
    Per
    -0.39
    Dieter
    -0.39
     rifer
    -0.39
    POSITIVE LOGITS
    arguments
    1.03
     argument
    1.02
     argue
    1.01
     arguments
    1.01
     Arguments
    0.99
     Argument
    0.97
    argue
    0.96
     arguing
    0.95
     argued
    0.95
     arg
    0.95
    Activations Density 0.093%

    No Known Activations