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. 8280
    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
    +0.25
    0.8%
    1915
    +0.06
    0.2%
    1120
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.25
    0.00
    0
    -0.06
    0.00
    1
    -0.05
    0.00
    Negative Logits
     unspeak
    -2.41
     reluct
    -2.04
     ineffec
    -1.99
     shenan
    -1.97
     impra
    -1.95
     unavoid
    -1.92
     indescri
    -1.91
     vainly
    -1.87
     disagre
    -1.82
     horrend
    -1.79
    POSITIVE LOGITS
    <bos>
    7.41
    GEBURTSDATUM
    1.78
    expandindo
    1.66
     Himo
    1.57
     Walkover
    1.50
     Paglinawan
    1.47
     Administrativna
    1.44
     betweenstory
    1.40
    Autoritní
    1.36
    OGND
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.