© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11623
    Prev
    Next
    INDEX
    Explanations

    mentions of thin objects or descriptors

    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
    1034
    +0.15
    0.5%
    899
    +0.13
    0.5%
    1145
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.15
    0.02
    1034
    +0.13
    0.02
    1793
    +0.13
    0.02
    Negative Logits
     autorytatywna
    -0.54
    Sucesor
    -0.50
     للاسماء
    -0.49
    Politique
    -0.49
     Meksiku
    -0.48
    Fprintf
    -0.47
    ZoneId
    -0.46
    RTSC
    -0.46
    Portale
    -0.44
    Demografía
    -0.44
    POSITIVE LOGITS
     thin
    1.23
     Thin
    1.12
    Thin
    1.07
    thin
    1.05
     thick
    1.02
     thinning
    0.97
     thinner
    0.95
     thinned
    0.94
     thickness
    0.94
    thick
    0.93
    Activations Density 0.068%

    No Known Activations