© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 610
    Prev
    Next
    INDEX
    Explanations

    the word "only" in various contexts

    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
    +0.19
    0.7%
    1994
    +0.10
    0.4%
    1385
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1981
    +0.19
    0.05
    1994
    +0.10
    0.04
    554
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.46
    ⓧ
    -1.12
    
    -0.95
     intersper
    -0.94
     enshr
    -0.82
    <?
    -0.74
     endow
    -0.73
    /***
    -0.72
     darted
    -0.71
     underval
    -0.70
    POSITIVE LOGITS
     Minang
    1.01
     tramont
    1.00
     saar
    0.99
     lavabo
    0.97
     uhr
    0.96
     riva
    0.95
     bandung
    0.94
     monaster
    0.94
     sirop
    0.94
     jati
    0.93
    Activations Density 0.144%

    No Known Activations