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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13446
    Prev
    Next
    INDEX
    Explanations

    phrases related to dialogue or communication

    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
    1233
    +0.11
    0.3%
    25
    +0.10
    0.3%
    1053
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1296
    +0.11
    0.03
    25
    +0.10
    0.03
    47
    +0.10
    0.02
    Negative Logits
     witcher
    -0.63
     lgbt
    -0.63
     celtic
    -0.59
     imprud
    -0.58
     excru
    -0.57
     cuck
    -0.57
     ufo
    -0.56
     livel
    -0.55
     madonna
    -0.54
     Nils
    -0.54
    POSITIVE LOGITS
     dirait
    0.72
     réuss
    0.66
     particolar
    0.61
     brille
    0.61
     augmenté
    0.60
    tvguidetime
    0.60
     conseille
    0.59
     saurait
    0.59
     constate
    0.59
    irmingham
    0.59
    Activations Density 0.161%

    No Known Activations