© 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. 12182
    Prev
    Next
    INDEX
    Explanations

    words related to food and eating

    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
    856
    +0.09
    0.3%
    906
    +0.09
    0.3%
    1013
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.09
    0.03
    128
    +0.09
    0.03
    751
    +0.08
    0.03
    Negative Logits
     caractéris
    -0.47
    ::::::::::::::::
    -0.46
     bascul
    -0.44
     énon
    -0.42
     éto
    -0.41
    @@@@@@@@
    -0.40
     catég
    -0.40
    şme
    -0.40
    Months
    -0.39
    asmussen
    -0.39
    POSITIVE LOGITS
     stopp
    0.72
     tomat
    0.58
     tiredness
    0.56
     quits
    0.56
     baig
    0.56
     adjourn
    0.55
     franz
    0.55
     drau
    0.55
     discontinue
    0.55
    Atsauces
    0.55
    Activations Density 0.444%

    No Known Activations