© 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. 11841
    Prev
    Next
    INDEX
    Explanations

    quotes and reported speech in sentences

    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
    599
    +0.17
    0.6%
    1577
    +0.15
    0.5%
    1224
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.17
    0.21
    1129
    +0.15
    0.16
    658
    +0.12
    0.15
    Negative Logits
     affor
    -2.55
     increa
    -2.47
     impra
    -2.42
     scrat
    -2.37
     excru
    -2.37
     suscep
    -2.37
     disagre
    -2.33
     reluct
    -2.33
     snoopy
    -2.32
     depic
    -2.32
    POSITIVE LOGITS
     [
    0.93
    …
    0.85
    ...
    0.85
    [
    0.83
     …
    0.81
     ...
    0.80
    ,”
    0.80
    ,"
    0.80
     really
    0.76
    "
    0.74
    Activations Density 4.040%

    No Known Activations