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. 3087
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about electronic devices, possibly focusing on smartphones

    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
    876
    +0.17
    0.5%
    1385
    +0.17
    0.5%
    1343
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.17
    0.05
    382
    +0.17
    0.03
    1446
    +0.15
    0.02
    Negative Logits
     Shakspeare
    -0.73
    <bos>
    -0.73
     pamph
    -0.71
     Maulana
    -0.70
     kemer
    -0.70
     Euripides
    -0.69
     spesifik
    -0.68
     Rumania
    -0.66
     Khart
    -0.66
     clergymen
    -0.66
    POSITIVE LOGITS
     trouva
    1.01
     écout
    0.86
     affez
    0.85
     voyant
    0.82
     specchio
    0.81
     cioc
    0.80
     dévou
    0.80
     porcelaine
    0.78
     regardant
    0.77
     bandai
    0.77
    Activations Density 0.221%

    No Known Activations