© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    important descriptive attributes and phrases that signify notable characteristics or qualities

    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
    0.9%
    1634
    +0.10
    0.4%
    871
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1556
    +0.24
    0.04
    1627
    +0.10
    0.04
    1867
    +0.08
    0.06
    Negative Logits
    <bos>
    -1.81
    BufferedWriter
    -0.66
    //});
    -0.63
    })();
    -0.60
    //---
    -0.60
    EUROPA
    -0.60
    Kontrola
    -0.59
    IsRequired
    -0.59
    Prest
    -0.59
    fputs
    -0.59
    POSITIVE LOGITS
     lele
    1.14
     maroc
    1.11
    capulco
    1.10
     felipe
    1.10
    !!</
    1.08
     marseille
    1.05
     😭😭
    1.04
     jaya
    1.03
     thuy
    1.02
     :'(
    1.01
    Activations Density 0.653%

    No Known Activations