© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1946
    Prev
    Next
    INDEX
    Explanations

    structures related to support or encouragement

    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
    +0.24
    1.0%
    50
    +0.24
    0.9%
    1978
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.24
    0.08
    1978
    +0.24
    0.05
    1699
    +0.08
    0.05
    Negative Logits
    <bos>
    -3.84
    ⓧ
    -0.97
    новништво
    -0.94
     Italijani
    -0.93
    <?
    
    -0.86
    contentLoaded
    -0.84
    Autoritní
    -0.82
    Personendaten
    -0.82
    /**
    -0.81
    Hentet
    -0.79
    POSITIVE LOGITS
     valencia
    0.99
     jaya
    0.97
     maroc
    0.96
     stockholm
    0.95
     santiago
    0.95
     gila
    0.94
     bandung
    0.94
     napoli
    0.90
     verona
    0.89
     wien
    0.89
    Activations Density 0.192%

    No Known Activations