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. 15545
    Prev
    Next
    INDEX
    Explanations

    genes and RNA related keywords

    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
    1896
    +0.15
    0.6%
    316
    +0.14
    0.6%
    1124
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.15
    0.09
    227
    +0.14
    0.09
    442
    +0.14
    0.04
    Negative Logits
     kark
    -0.86
     agrico
    -0.81
     kuli
    -0.79
     kuku
    -0.79
    capulco
    -0.79
     naran
    -0.78
     beren
    -0.77
    licante
    -0.77
     bandung
    -0.77
     furg
    -0.76
    POSITIVE LOGITS
     Shakspeare
    1.29
     McLaugh
    1.23
     unwarran
    1.11
     gaily
    1.07
     disagre
    1.05
     beaute
    1.02
     impra
    1.02
     increa
    1.00
     Shaksp
    0.97
     Eccle
    0.97
    Activations Density 0.513%

    No Known Activations