Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6356
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographical location, "Richmond."

    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
    410
    +0.16
    0.9%
    25
    +0.15
    0.8%
    1492
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1741
    +0.16
    -0.00
    690
    +0.15
    0.04
    1328
    +0.14
    0.04
    Negative Logits
    ⓧ
    -0.71
     pinulongan
    -0.67
    <bos>
    -0.67
    /**
    -0.61
     NSCoder
    -0.59
    Touchable
    -0.57
    AndroidJUnit
    -0.55
    AutoScale
    -0.55
    ganu
    -0.55
    HttpPut
    -0.54
    POSITIVE LOGITS
     Richmond
    0.89
     pank
    0.87
     kasa
    0.86
    Richmond
    0.85
     duk
    0.79
     surabaya
    0.79
     jati
    0.78
     susun
    0.77
     jir
    0.76
     parati
    0.76
    Activations Density 0.697%

    No Known Activations