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. 1538
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related terms

    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
    +0.18
    0.5%
    2034
    +0.16
    0.5%
    1699
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1169
    +0.18
    0.03
    1216
    +0.16
    0.02
    876
    +0.12
    0.00
    Negative Logits
     ujedno
    -1.08
     katastro
    -0.91
     Punj
    -0.87
     empêche
    -0.84
     Czechos
    -0.84
     conflic
    -0.83
     dépasse
    -0.82
     entraîne
    -0.82
     kompres
    -0.81
     konflik
    -0.80
    POSITIVE LOGITS
    uteurs
    0.93
     Chinois
    0.89
     COOKIE
    0.86
     lapin
    0.82
     espé
    0.79
     mignon
    0.77
     veau
    0.77
     auguri
    0.77
     coq
    0.77
     {;
    0.77
    Activations Density 0.078%

    No Known Activations