© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and their actions or controversies

    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
    +0.34
    1.4%
    604
    +0.16
    0.7%
    1253
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1253
    +0.34
    0.05
    617
    +0.16
    0.08
    751
    +0.13
    0.06
    Negative Logits
    <bos>
    -2.60
     stric
    -0.80
     finn
    -0.80
     fto
    -0.80
     regis
    -0.79
     purs
    -0.77
     eam
    -0.76
     oun
    -0.76
     inder
    -0.75
     gie
    -0.75
    POSITIVE LOGITS
     Joaqu
    1.24
     Áng
    1.17
     Belén
    1.14
     Valentín
    1.11
     Mónica
    1.11
     Leopoldo
    1.11
     Palembang
    1.08
     Muhamma
    1.05
     Compañ
    1.05
     véhic
    1.04
    Activations Density 2.385%

    No Known Activations