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. 8202
    Prev
    Next
    INDEX
    Explanations

    points of emphasis or importance 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
    481
    +0.14
    0.5%
    1677
    +0.12
    0.5%
    699
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.14
    0.03
    481
    +0.12
    0.02
    1677
    +0.12
    0.02
    Negative Logits
     Décembre
    -0.86
     compréhen
    -0.81
     Perci
    -0.77
     sappi
    -0.77
     Février
    -0.76
     Messieurs
    -0.74
     Áng
    -0.74
     gettyimages
    -0.73
     Secrétaire
    -0.70
     depositphotos
    -0.68
    POSITIVE LOGITS
     highlights
    1.13
     highlight
    1.13
     highlighting
    1.02
     highlighted
    0.96
    highlight
    0.94
    Highlight
    0.89
     Highlight
    0.89
     Highlights
    0.89
    highlights
    0.88
    Highlights
    0.83
    Activations Density 0.078%

    No Known Activations