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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 568
    Prev
    Next
    INDEX
    Explanations

    references to specific classes of naval vessels

    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
    +0.20
    0.8%
    1145
    +0.10
    0.4%
    1705
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.20
    0.10
    1343
    +0.10
    0.10
    1597
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.44
     intersper
    -1.02
     disbur
    -0.82
     endow
    -0.77
    <?
    
    -0.75
     ratify
    -0.73
     harmonize
    -0.73
    
    
    -0.73
     gratify
    -0.71
    /***
    
    -0.71
    POSITIVE LOGITS
     Kategor
    0.72
    erenc
    0.70
     smtplib
    0.67
     psycopg
    0.67
     vne
    0.67
    zsef
    0.66
     silikon
    0.66
     kredi
    0.65
     karton
    0.65
    öyle
    0.65
    Activations Density 0.864%

    No Known Activations