© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 11940
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or communities

    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
    897
    +0.13
    0.5%
    220
    +0.12
    0.5%
    120
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.13
    0.03
    991
    +0.12
    0.02
    513
    +0.12
    0.02
    Negative Logits
     fidu
    -0.76
     accla
    -0.74
    FTFY
    -0.72
    Ehh
    -0.70
    Lmfao
    -0.69
    Noice
    -0.67
     shenan
    -0.66
    Lma
    -0.66
     logarith
    -0.66
     disreg
    -0.66
    POSITIVE LOGITS
     neighborhood
    1.44
     neighborhoods
    1.24
     Neighborhood
    1.24
    Neighborhood
    1.21
    neighborhood
    1.21
     neighbor
    1.20
     neighbors
    1.20
     neighbourhood
    1.17
    bourhood
    1.13
    neighbors
    1.02
    Activations Density 0.069%

    No Known Activations