© 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. 4242
    Prev
    Next
    INDEX
    Explanations

    references to locations like cities, towns, clubs, teams, schools, and stations

    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
    1870
    +0.13
    0.4%
    513
    +0.12
    0.3%
    1438
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    513
    +0.13
    0.05
    220
    +0.12
    0.06
    666
    +0.10
    0.04
    Negative Logits
     increa
    -1.51
     impra
    -1.44
     depic
    -1.40
     intermitt
    -1.39
     guarante
    -1.37
     inev
    -1.36
     effe
    -1.36
     reluct
    -1.36
     perfet
    -1.33
     erad
    -1.33
    POSITIVE LOGITS
    ’
    0.95
    '
    0.95
     itself
    0.80
    wide
    0.72
    &#
    0.67
    ׳
    0.67
    €™
    0.67
    `
    0.66
    ´
    0.66
    â
    0.65
    Activations Density 0.301%

    No Known Activations