© 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. 4582
    Prev
    Next
    INDEX
    Explanations

    names and terms related to medicine and healthcare

    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
    1842
    +0.22
    0.8%
    1343
    +0.18
    0.7%
    50
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.22
    0.08
    227
    +0.18
    0.08
    198
    +0.17
    0.08
    Negative Logits
    <bos>
    -1.44
    /***
    -0.95
     intersper
    -0.94
    <?
    -0.84
     adjour
    -0.83
     underval
    -0.81
     allude
    -0.80
     incarcer
    -0.78
     subsist
    -0.74
     chanced
    -0.74
    POSITIVE LOGITS
     montagna
    0.83
     signora
    0.83
     croce
    0.83
     polizia
    0.82
     riva
    0.82
     BIBSYS
    0.80
     paradiso
    0.79
     papà
    0.79
    esticides
    0.78
     monaster
    0.77
    Activations Density 0.616%

    No Known Activations