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. 2811
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical terms including numbers and symbols

    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
    394
    +0.27
    1.1%
    50
    +0.26
    1.0%
    964
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.27
    0.20
    964
    +0.26
    0.14
    50
    +0.14
    0.30
    Negative Logits
    TagMode
    -0.97
    <bos>
    -0.96
    IsContent
    -0.85
     ""],
    -0.82
     Drapeau
    -0.81
     NKC
    -0.80
    DoubleQuotes
    -0.79
     Wikispecies
    -0.79
     FBref
    -0.78
     typelib
    -0.77
    POSITIVE LOGITS
     impra
    1.60
     maneu
    1.45
     reluct
    1.44
     affor
    1.44
     unden
    1.42
     inev
    1.42
     uninten
    1.39
     increa
    1.38
     Rine
    1.37
     shenan
    1.36
    Activations Density 12.898%

    No Known Activations