© 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. 6886
    Prev
    Next
    INDEX
    Explanations

    adjectives and participles related to food

    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
    1177
    +0.19
    0.6%
    1385
    +0.15
    0.5%
    198
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.19
    0.07
    946
    +0.15
    0.06
    1385
    +0.14
    0.05
    Negative Logits
     lapto
    -0.76
    rungsseite
    -0.76
     ***!
    -0.72
     moze
    -0.68
    (">>
    -0.67
    ]='\
    -0.66
     jubile
    -0.66
     OFDb
    -0.66
     nawr
    -0.65
    LEn
    -0.64
    POSITIVE LOGITS
     inext
    1.11
     Juf
    1.10
     Gorb
    1.05
     depic
    1.02
     secon
    1.00
     disagre
    0.98
     hentai
    0.97
     emphat
    0.97
     reluct
    0.97
     caprice
    0.97
    Activations Density 0.443%

    No Known Activations