© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5150
    Prev
    Next
    INDEX
    Explanations

    locations or landmarks near bodies of water

    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
    1120
    +0.13
    0.4%
    906
    +0.13
    0.4%
    939
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.13
    0.05
    110
    +0.13
    0.03
    1300
    +0.11
    0.03
    Negative Logits
     klap
    -0.80
     kram
    -0.72
     krab
    -0.70
     lapto
    -0.70
     hek
    -0.69
    XmlEnum
    -0.69
     maksi
    -0.68
     elek
    -0.67
     moza
    -0.65
     bera
    -0.64
    POSITIVE LOGITS
     ecru
    0.83
     swarovski
    0.78
     trône
    0.76
     vœ
    0.75
     ftu
    0.74
     réfugi
    0.73
     idolat
    0.72
     eiffel
    0.71
     malheur
    0.70
     inext
    0.69
    Activations Density 0.254%

    No Known Activations