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

    Neuronpedia

    Jacobian LensNEW
    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. 5335
    Prev
    Next
    INDEX
    Explanations

    mentions or questions using the word "Did" or the negation "did not"

    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
    32
    +0.11
    0.4%
    314
    +0.11
    0.4%
    489
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.11
    0.05
    950
    +0.11
    0.04
    169
    +0.10
    0.04
    Negative Logits
     auri
    -0.76
     philipp
    -0.76
     myr
    -0.73
     emper
    -0.72
     oner
    -0.72
     bourgeo
    -0.71
     buc
    -0.70
     napoli
    -0.70
     sura
    -0.70
     fluo
    -0.69
    POSITIVE LOGITS
     Did
    1.00
     did
    1.00
    did
    0.99
    Did
    0.90
     DID
    0.86
    DID
    0.81
    didn
    0.71
     didn
    0.68
     todella
    0.63
     didnt
    0.62
    Activations Density 0.152%

    No Known Activations