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. 1539
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities mentioned in a text

    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
    1967
    +0.17
    0.6%
    674
    +0.14
    0.5%
    1053
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.17
    0.04
    1416
    +0.14
    0.03
    341
    +0.10
    0.04
    Negative Logits
    raught
    -0.53
    SpringBootTest
    -0.53
    !("{
    -0.52
    FloatField
    -0.52
     Daarna
    -0.51
     Daarom
    -0.50
    addContainerGap
    -0.50
    İstinadlar
    -0.49
    AfterClass
    -0.48
    Daar
    -0.47
    POSITIVE LOGITS
     mef
    0.92
     aen
    0.87
    fordable
    0.86
     migra
    0.83
     territo
    0.83
     lele
    0.82
     fup
    0.81
     ftu
    0.80
     teneb
    0.80
     minuta
    0.79
    Activations Density 0.121%

    No Known Activations