© 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 EvalsExportsinterp-engineNEWAPI 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. 16339
    Prev
    Next
    INDEX
    Explanations

    the word "dig" and its variations

    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
    871
    +0.17
    0.6%
    874
    +0.14
    0.5%
    82
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    871
    +0.17
    0.03
    1872
    +0.14
    0.03
    82
    +0.13
    0.03
    Negative Logits
     karton
    -0.55
     kanton
    -0.51
     kond
    -0.50
     kosme
    -0.49
     bunda
    -0.49
     klinik
    -0.49
    rativa
    -0.47
     ikon
    -0.47
     eko
    -0.46
     Gelder
    -0.46
    POSITIVE LOGITS
     dug
    1.19
     digging
    1.18
     dig
    1.14
     digs
    1.04
    Dig
    1.04
     Dig
    1.04
     digger
    1.02
    dig
    0.92
     DIG
    0.89
    Dug
    0.84
    Activations Density 0.073%

    No Known Activations