© 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. 123
    Prev
    Next
    INDEX
    Explanations

    phrases indicating noteworthy achievements or performances

    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
    1.3%
    1351
    +0.11
    0.4%
    1967
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1643
    +0.34
    0.04
    1351
    +0.11
    0.03
    1731
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.72
    ⓧ
    -1.07
    
    
    -0.93
    <?
    -0.85
    /**
    -0.75
     strove
    -0.63
     endeavoured
    -0.61
    <?
    
    -0.60
     disbur
    -0.58
     endow
    -0.58
    POSITIVE LOGITS
    trás
    1.12
     Portugu
    1.11
     ados
    1.09
     Minang
    1.04
     palio
    1.02
     churras
    1.02
     epoca
    1.02
    lindo
    1.02
     lavander
    1.01
     Comandante
    1.01
    Activations Density 0.135%

    No Known Activations