© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14241
    Prev
    Next
    INDEX
    Explanations

    invitations or calls to action to join a group or cause

    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
    1793
    +0.10
    0.3%
    1043
    +0.09
    0.3%
    1210
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1210
    +0.10
    0.02
    1861
    +0.09
    0.03
    320
    +0.08
    0.01
    Negative Logits
     Produit
    -0.72
     thuy
    -0.71
     lele
    -0.68
     kien
    -0.66
    SneakyThrows
    -0.64
     Ouv
    -0.62
     Chambres
    -0.62
     mahd
    -0.61
     jawa
    -0.61
     Lég
    -0.59
    POSITIVE LOGITS
     NDEBUG
    0.67
     mazda
    0.59
     gtx
    0.57
     subaru
    0.57
     lgbt
    0.54
     downvotes
    0.54
     ryzen
    0.53
     outlander
    0.52
     chrysler
    0.50
     corsair
    0.50
    Activations Density 0.210%

    No Known Activations