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. 644
    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
    1.1%
    1871
    +0.06
    0.2%
    1120
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    -0.28
    0.00
    0
    -0.06
    0.00
    1
    -0.06
    0.00
    Negative Logits
    ,
    -1.74
     to
    -1.62
     in
    -1.60
     for
    -1.58
     as
    -1.57
     and
    -1.57
     
    -1.56
     not
    -1.55
     so
    -1.55
     that
    -1.53
    POSITIVE LOGITS
    <bos>
    9.43
     fatis
    2.95
     ftu
    2.92
     Ottobre
    2.90
     sappi
    2.90
     ordina
    2.84
     paff
    2.80
     Luglio
    2.77
     poft
    2.75
     quæ
    2.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.