© 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. 3187
    Prev
    Next
    INDEX
    Explanations

    emotionally expressive symbols and emojis in a context related to events or activities

    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
    897
    +0.12
    0.6%
    1343
    +0.12
    0.6%
    1325
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.12
    0.10
    227
    +0.12
    0.07
    1363
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.32
    Institu
    -0.99
    Nascimento
    -0.95
     do
    -0.94
    Comun
    -0.94
    Asoci
    -0.94
     post
    -0.91
    Pod
    -0.91
    꿔
    -0.91
    Pró
    -0.90
    POSITIVE LOGITS
     stockholm
    3.36
     increa
    3.05
     eiffel
    3.05
     wien
    3.01
     madonna
    3.01
     unden
    3.01
     milano
    3.01
     squa
    3.01
     michelin
    2.98
     ?...
    2.92
    Activations Density 0.770%

    No Known Activations