© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2634
    Prev
    Next
    INDEX
    Explanations

    geographical locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.27
    1.0%
    939
    +0.11
    0.4%
    1967
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.27
    0.07
    964
    +0.11
    0.05
    227
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.36
    <eos>
    -0.68
    @
    -0.66
    ///**
    -0.65
    private
    -0.65
    !
    -0.64
    0
    -0.63
    public
    -0.63
    PEAT
    -0.63
    2
    -0.61
    POSITIVE LOGITS
     Juf
    1.89
     fta
    1.84
     ftu
    1.82
     squa
    1.80
     fep
    1.79
     unwarran
    1.78
     aen
    1.73
     sovere
    1.73
     fup
    1.69
     nece
    1.69
    Activations Density 0.336%

    No Known Activations