© 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. 10844
    Prev
    Next
    INDEX
    Explanations

    mentions of specific labels or tags within a text

    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
    812
    +0.16
    0.7%
    481
    +0.15
    0.6%
    298
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.16
    0.03
    812
    +0.15
    0.02
    1622
    +0.14
    0.02
    Negative Logits
     Võ
    -0.79
     bunda
    -0.66
     Bá
    -0.57
     balon
    -0.56
    dolu
    -0.54
    dö
    -0.54
     soto
    -0.54
     kamb
    -0.53
     rú
    -0.53
     Morelos
    -0.52
    POSITIVE LOGITS
     tag
    1.53
     Tag
    1.44
     tags
    1.43
    tag
    1.34
    Tag
    1.34
     tagging
    1.31
     Tags
    1.30
    tags
    1.27
     tagged
    1.21
     TAG
    1.19
    Activations Density 0.065%

    No Known Activations