© 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. 11980
    Prev
    Next
    INDEX
    Explanations

    phrases discussing the implications of potential actions

    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
    1328
    +0.15
    0.5%
    481
    +0.11
    0.4%
    478
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.15
    0.08
    481
    +0.11
    0.06
    1425
    +0.11
    0.06
    Negative Logits
     habile
    -0.88
     wien
    -0.73
     écla
    -0.73
     éto
    -0.71
     obé
    -0.70
     joyeux
    -0.68
     vété
    -0.68
     soigne
    -0.67
     masaj
    -0.66
     franz
    -0.66
    POSITIVE LOGITS
     would
    1.00
    would
    0.94
     WOULD
    0.90
     Would
    0.87
    Would
    0.84
     wouldn
    0.83
    wouldn
    0.75
     wouldnt
    0.73
     could
    0.65
     Wouldn
    0.64
    Activations Density 0.202%

    No Known Activations