© 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. 10-RES-JB
    11. 4328
    Prev
    Next
    INDEX
    Explanations

    references to climate change data and trends

    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
    +0.26
    0.9%
    776
    +0.11
    0.4%
    1036
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.26
    0.03
    1161
    +0.11
    0.03
    1658
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.43
    /*
    -0.59
    //@
    -0.58
    ⓧ
    -0.58
    },{
    -0.55
    queryInterface
    -0.53
    public
    -0.53
    <?
    -0.52
    /**
    -0.52
    Referències
    -0.52
    POSITIVE LOGITS
     maneu
    1.34
     lidl
    1.19
     accla
    1.14
     bayern
    1.14
     chrysler
    1.13
     milf
    1.12
     calum
    1.12
     eiffel
    1.12
     toledo
    1.11
     Czechos
    1.11
    Activations Density 0.356%

    No Known Activations