© 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. 4660
    Prev
    Next
    INDEX
    Explanations

    instances of specific situations or controversies referenced in a text

    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
    1253
    +0.12
    0.4%
    764
    +0.12
    0.4%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.12
    0.06
    875
    +0.12
    0.04
    74
    +0.10
    0.04
    Negative Logits
     kram
    -0.73
     solidar
    -0.73
     republi
    -0.70
     uhr
    -0.65
     trast
    -0.65
     ideolog
    -0.63
     sels
    -0.62
     vermel
    -0.61
     alkoh
    -0.61
     unknownFields
    -0.61
    POSITIVE LOGITS
     nor
    0.77
     or
    0.74
     anything
    0.68
    anything
    0.65
     или
    0.63
     newArr
    0.63
     NDEBUG
    0.62
     eller
    0.62
     Tampoco
    0.62
     aught
    0.60
    Activations Density 0.907%

    No Known Activations