© 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. 4651
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    1343
    +0.35
    1.3%
    1253
    +0.15
    0.6%
    184
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.35
    0.06
    1969
    +0.15
    0.03
    865
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.73
    مرح
    -0.81
    osoba
    -0.81
    Према
    -0.80
    Zdroje
    -0.80
    Lähteet
    -0.78
    Unmarshaller
    -0.77
    Asoci
    -0.77
     mergeFrom
    -0.76
    FXMLLoader
    -0.76
    POSITIVE LOGITS
     stockholm
    1.94
     bordeaux
    1.90
     haup
    1.88
     wien
    1.85
     lill
    1.76
     lidl
    1.75
     ?...
    1.75
     noel
    1.75
     strick
    1.74
     napoli
    1.74
    Activations Density 0.092%

    No Known Activations