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. 15523
    Prev
    Next
    INDEX
    Explanations

    technical information related to data migration and network connectivity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    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
    1577
    +0.12
    0.3%
    453
    +0.10
    0.3%
    1967
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.12
    0.05
    1434
    +0.10
    0.04
    1770
    +0.08
    0.04
    Negative Logits
    Δείτε
    -0.62
    /**
    -0.59
    Ainsi
    -0.55
    Cependant
    -0.54
    Solución
    -0.54
    Πηγή
    -0.53
     Paglinawan
    -0.52
    Kilde
    -0.51
    VYMaps
    -0.51
    Lorsque
    -0.51
    POSITIVE LOGITS
     friable
    0.93
     jati
    0.92
     deleter
    0.89
     jaya
    0.88
     blos
    0.83
     idr
    0.82
     carina
    0.82
     mosso
    0.82
     suscep
    0.82
     scrat
    0.81
    Activations Density 0.207%

    No Known Activations