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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8438
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS class attributes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.13
    0.4%
    919
    +0.09
    0.3%
    453
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1989
    +0.13
    0.02
    1478
    +0.09
    0.02
    724
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.86
    ,
    -0.78
     
    -0.77
    …
    -0.76
    .
    -0.75
     (
    -0.74
     since
    -0.74
      
    -0.74
     between
    -0.73
     to
    -0.72
    POSITIVE LOGITS
     unce
    2.02
     squa
    2.00
     unden
    2.00
     scrat
    1.98
     increa
    1.97
     affor
    1.92
     michelin
    1.92
     quoique
    1.91
     guarante
    1.91
     ?...
    1.88
    Activations Density 0.043%

    No Known Activations