© 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. 14812
    Prev
    Next
    INDEX
    Explanations

    German words that are related to textiles and clothing

    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
    381
    +0.12
    0.4%
    203
    +0.10
    0.3%
    1190
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    523
    +0.12
    0.01
    1190
    +0.10
    0.02
    1788
    +0.09
    0.01
    Negative Logits
    JScrollPane
    -0.68
     realice
    -0.64
    Threading
    -0.63
    glUniform
    -0.62
     enví
    -0.60
    Argumento
    -0.59
    toISOString
    -0.59
     utilice
    -0.58
    marginVertical
    -0.58
    {{--
    -0.57
    POSITIVE LOGITS
     Pamph
    1.13
     philanth
    1.05
     sputnik
    1.02
     michelin
    1.02
     ariel
    1.00
     pamph
    1.00
     peppa
    0.98
     swarovski
    0.98
     conspic
    0.97
     loren
    0.97
    Activations Density 0.080%

    No Known Activations