© 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. 4605
    Prev
    Next
    INDEX
    Explanations

    numerical expressions related to timeframes or durations

    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
    +0.20
    0.8%
    776
    +0.15
    0.6%
    1535
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.20
    0.09
    1978
    +0.15
    0.07
    1910
    +0.14
    0.06
    Negative Logits
    <bos>
    -2.51
     belangrij
    -0.78
    ⓧ
    -0.77
    
    -0.70
    },[])
    -0.69
    <?
    -0.68
    GRAPHS
    -0.67
    ;%%
    -0.65
    };*/
    -0.65
    })*/
    -0.65
    POSITIVE LOGITS
     socie
    1.03
     revan
    0.96
     potest
    0.93
     Cfr
    0.92
     monaster
    0.91
     combusti
    0.90
     gubern
    0.89
     magis
    0.88
    Rgds
    0.86
    tldr
    0.85
    Activations Density 0.229%

    No Known Activations