© 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. 10962
    Prev
    Next
    INDEX
    Explanations

    the verb "is" followed by other words or phrases indicating descriptions, states, or qualities

    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
    1937
    +0.18
    0.6%
    1531
    +0.10
    0.3%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.18
    0.10
    394
    +0.10
    0.05
    204
    +0.10
    0.04
    Negative Logits
     kasa
    -1.02
     silikon
    -1.02
     maksi
    -0.94
     kafe
    -0.93
     saha
    -0.92
     kase
    -0.90
     seksi
    -0.90
     keramik
    -0.86
     karton
    -0.86
     karna
    -0.85
    POSITIVE LOGITS
    Cześć
    0.69
     always
    0.67
    Dziękuję
    0.66
    toprule
    0.62
     definitely
    0.61
     prosciutto
    0.60
     usually
    0.60
    Witaj
    0.60
    Toujours
    0.58
     often
    0.58
    Activations Density 0.388%

    No Known Activations