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. 8182
    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
    +0.28
    1.0%
    1648
    +0.04
    0.2%
    200
    +0.04
    0.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.28
    0.00
    0
    -0.04
    0.00
    1
    -0.04
    0.00
    Negative Logits
     reluct
    -4.43
     shenan
    -4.34
     impra
    -4.32
     unspeak
    -4.31
     increa
    -4.23
     disagre
    -4.14
     depic
    -4.05
     maneu
    -4.00
     apprehen
    -3.92
     indestru
    -3.92
    POSITIVE LOGITS
    <bos>
    9.37
     Paglinawan
    2.10
     Walkover
    2.08
     betweenstory
    2.07
    expandindo
    2.02
     '\\;'
    2.01
    GEBURTSDATUM
    2.00
    Autoritní
    1.94
     Himo
    1.92
    脚注の使い方
    1.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.