© 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. 2266
    Prev
    Next
    INDEX
    Explanations

    information related to upcoming technology releases

    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
    +0.34
    1.4%
    1177
    +0.14
    0.6%
    690
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1403
    +0.34
    0.02
    678
    +0.14
    0.06
    227
    +0.12
    0.06
    Negative Logits
    <bos>
    -2.87
    ⓧ
    -1.22
     quitted
    -1.06
    /**
    -1.01
     ftre
    -0.98
     cabrio
    -0.91
     fhould
    -0.90
     fince
    -0.90
     beft
    -0.89
     defire
    -0.88
    POSITIVE LOGITS
     considér
    0.71
     conftest
    0.70
     montagna
    0.69
     incontour
    0.68
     bosco
    0.67
     effray
    0.67
     riva
    0.66
     malheureux
    0.64
     epoca
    0.62
     Applicability
    0.61
    Activations Density 0.836%

    No Known Activations