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. 5329
    Prev
    Next
    INDEX
    Explanations

    information related to academic studies in the field of medical research

    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
    1343
    +0.22
    0.9%
    227
    +0.16
    0.6%
    1804
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.22
    0.15
    282
    +0.16
    0.09
    1343
    +0.14
    0.10
    Negative Logits
    <bos>
    -2.50
    ⓧ
    -0.86
    /**
    -0.85
    
    
    -0.81
     betweenstory
    -0.75
    SourceChecksum
    -0.74
    MessageOf
    -0.74
     propOrder
    -0.74
    <?
    
    -0.70
    <?
    -0.69
    POSITIVE LOGITS
     idr
    1.09
     „,
    1.07
     cannes
    1.06
     lele
    1.05
     §.
    1.04
     kaos
    1.04
     vasi
    1.04
     meis
    1.04
     franz
    1.03
     Nö
    1.02
    Activations Density 0.892%

    No Known Activations