© 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. 2455
    Prev
    Next
    INDEX
    Explanations

    references to database operations and data querying

    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
    +0.17
    0.7%
    876
    +0.16
    0.6%
    1699
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.17
    0.00
    1699
    +0.16
    0.05
    1445
    +0.15
    0.04
    Negative Logits
    <bos>
    -3.21
    
    -1.09
    ⓧ
    -1.02
    <?
    -1.01
    /**
    -1.00
    /*
    -0.94
    <?
    -0.80
    glMatrixMode
    -0.76
    EndGlobalSection
    -0.71
    })();
    -0.69
    POSITIVE LOGITS
     doman
    1.18
     unden
    1.13
     grati
    1.11
     dises
    1.11
     coq
    1.06
    arture
    1.06
     ?...
    1.02
     lyon
    1.01
     parma
    1.01
     illi
    1.01
    Activations Density 0.159%

    No Known Activations