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. 1466
    Prev
    Next
    INDEX
    Explanations

    scientific journal citations

    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
    283
    +0.17
    0.5%
    906
    +0.13
    0.4%
    1741
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.17
    0.01
    924
    +0.13
    0.02
    718
    +0.11
    0.02
    Negative Logits
     sculptured
    -1.14
     boughs
    -1.12
     unspeak
    -1.09
     tupperware
    -1.05
     cushi
    -1.04
     shenan
    -0.93
     gaily
    -0.93
     fringed
    -0.91
     McLaugh
    -0.91
     hairc
    -0.91
    POSITIVE LOGITS
     Kategor
    1.73
     alkoh
    1.68
     elek
    1.67
     stoff
    1.62
     makro
    1.60
     antik
    1.59
     marte
    1.59
     fré
    1.57
     Strukt
    1.54
     biograf
    1.53
    Activations Density 0.077%

    No Known Activations