© 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. 12538
    Prev
    Next
    INDEX
    Explanations

    instances of the word "means" used in various contexts

    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
    1233
    +0.19
    0.7%
    32
    +0.17
    0.6%
    938
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1233
    +0.19
    0.04
    938
    +0.17
    0.04
    1983
    +0.17
    0.04
    Negative Logits
    dP
    -0.50
     optik
    -0.50
     Roper
    -0.49
     Tübingen
    -0.47
     Antik
    -0.47
     Verk
    -0.47
     Frö
    -0.45
    憤
    -0.45
     Gelder
    -0.45
     kura
    -0.45
    POSITIVE LOGITS
     MEAN
    1.00
    means
    0.98
     mean
    0.97
    Mean
    0.97
     MEANS
    0.95
     Mean
    0.95
     Means
    0.95
     coar
    0.94
    Means
    0.93
     affez
    0.93
    Activations Density 0.070%

    No Known Activations