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. 16081
    Prev
    Next
    INDEX
    Explanations

    references to healthcare providers and related entities

    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
    1870
    +0.14
    0.5%
    1507
    +0.11
    0.4%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.05
    1507
    +0.11
    0.03
    1531
    +0.10
    0.04
    Negative Logits
     résoudre
    -0.59
     transmettre
    -0.58
     satisfaire
    -0.56
     générer
    -0.55
    springboot
    -0.54
     régler
    -0.53
     couvrir
    -0.53
     appeler
    -0.53
     prévoir
    -0.52
     arrêter
    -0.52
    POSITIVE LOGITS
     maksi
    0.91
     alha
    0.88
     keramik
    0.88
     Suom
    0.87
     kafe
    0.87
     saar
    0.87
     tenda
    0.84
     uhr
    0.82
     Ukraina
    0.78
     naer
    0.77
    Activations Density 0.199%

    No Known Activations