© 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. 6-RES-JB
    11. 6611
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, Hindu deities, and ancient Indian cultural elements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.15
    0.5%
    1435
    +0.07
    0.3%
    1480
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.15
    0.04
    1278
    +0.07
    0.03
    1343
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.88
    ⓧ
    -0.80
    </thead>
    -0.66
     złotych
    -0.65
     avesse
    -0.64
    hnia
    -0.62
    ">—
    -0.61
    Fordítás
    -0.61
     himo
    -0.60
    ersonal
    -0.60
    POSITIVE LOGITS
     affor
    1.93
     maneu
    1.76
     unspeak
    1.74
     indescri
    1.72
     madonna
    1.70
     unden
    1.69
     snoopy
    1.68
     impra
    1.68
     hairc
    1.68
     emphat
    1.67
    Activations Density 0.133%

    No Known Activations