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. 10061
    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%
    1967
    +0.05
    0.2%
    147
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.28
    0.00
    0
    -0.05
    0.00
    1
    -0.05
    0.00
    Negative Logits
     unspeak
    -2.59
     unwarran
    -2.14
     shenan
    -2.11
     unlaw
    -2.09
     disagre
    -2.09
     reluct
    -2.05
     impractica
    -2.04
     exasper
    -2.03
     ineffec
    -2.02
     indescri
    -2.01
    POSITIVE LOGITS
    <bos>
    9.36
    expandindo
    1.80
    Autoritní
    1.74
    GEBURTSDATUM
    1.71
     Walkover
    1.64
     betweenstory
    1.63
     Himo
    1.59
    Personendaten
    1.55
     дописавши
    1.53
     <>",
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.