© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1836
    Prev
    Next
    INDEX
    Explanations

    places, particularly locations and landmarks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1407
    +0.10
    0.4%
    1013
    +0.10
    0.3%
    161
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.10
    0.05
    1385
    +0.10
    0.04
    1975
    +0.08
    0.03
    Negative Logits
    <bos>
    -0.95
     try
    -0.58
     align
    -0.57
     hold
    -0.57
     make
    -0.56
    ਿੱ
    -0.56
    ണ്ട
    -0.56
     respond
    -0.56
    േ
    -0.55
     put
    -0.55
    POSITIVE LOGITS
     ecru
    1.62
     swarovski
    1.53
     jurassic
    1.39
     liberality
    1.38
     madonna
    1.34
     jacobs
    1.33
     eiffel
    1.33
     ibiza
    1.31
     bordeaux
    1.29
     lamborghini
    1.28
    Activations Density 0.217%

    No Known Activations