Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1756
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    674
    +0.22
    0.7%
    752
    +0.06
    0.2%
    392
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.22
    0.00
    0
    -0.06
    0.00
    1
    -0.05
    0.00
    Negative Logits
     reluct
    -8.80
     increa
    -8.51
     impra
    -8.48
     shenan
    -8.37
     depic
    -8.23
     disagre
    -8.21
     encomp
    -8.19
     affor
    -8.02
     unspeak
    -7.95
     maneu
    -7.93
    POSITIVE LOGITS
    <bos>
    8.05
     Walkover
    3.12
     Paglinawan
    2.67
     Himo
    2.54
     ***!
    2.52
     Baillargeon
    2.46
     himo
    2.45
     '\\;'
    2.43
     insuffisamment
    2.38
     Réponses
    2.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.