© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 4047
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used in various contexts, indicating their significance in the text

    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
    +0.24
    1.3%
    1961
    +0.12
    0.6%
    411
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.24
    0.04
    1961
    +0.12
    0.04
    382
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.20
     intersper
    -1.39
     encomp
    -1.14
    ⓧ
    -1.08
     endow
    -1.02
    /***
    
    -1.00
     unve
    -0.99
     superintend
    -0.98
     shenan
    -0.97
    
    
    -0.96
    POSITIVE LOGITS
    ;");
    0.73
    =""/>
    0.71
    _;
    0.70
    ;
    0.69
    °;
    0.68
    '];
    0.68
     galeria
    0.67
     ;$
    0.66
    ];
    0.66
    %;
    0.65
    Activations Density 0.083%

    No Known Activations