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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 9062
    Prev
    Next
    INDEX
    Explanations

    terms related to nuclear energy and technology

    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
    +0.17
    0.6%
    874
    +0.09
    0.3%
    1618
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.17
    0.04
    342
    +0.09
    0.04
    62
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.02
     pull
    -0.60
     distribute
    -0.58
     hold
    -0.56
     org
    -0.54
     mergeFrom
    -0.54
    葛
    -0.54
     cầu
    -0.54
     join
    -0.53
     pay
    -0.53
    POSITIVE LOGITS
     ecru
    1.34
     bordeaux
    1.33
     santiago
    1.28
     ibiza
    1.23
     Darío
    1.22
     murano
    1.20
     Mejía
    1.19
     mallorca
    1.18
     isuzu
    1.18
     hcm
    1.18
    Activations Density 0.244%

    No Known Activations