© 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. 4460
    Prev
    Next
    INDEX
    Explanations

    specific geographic or location-based information

    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
    406
    +0.17
    0.8%
    1937
    +0.13
    0.6%
    517
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.17
    0.02
    517
    +0.13
    0.01
    537
    +0.12
    0.02
    Negative Logits
     Connelly
    -0.47
    setopt
    -0.45
     Ple
    -0.44
    extr
    -0.44
    bootstrapcdn
    -0.44
    Doe
    -0.43
    oquia
    -0.43
    ecx
    -0.42
    Las
    -0.42
     Canaan
    -0.42
    POSITIVE LOGITS
     Ward
    1.42
    Ward
    1.37
     ward
    1.36
     WARD
    1.31
     wards
    1.09
    ward
    1.00
    WARD
    0.99
     sergio
    0.91
     ricardo
    0.90
     alberto
    0.87
    Activations Density 0.129%

    No Known Activations