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. 2904
    Prev
    Next
    INDEX
    Explanations

    descriptions of technical features in software development

    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
    876
    +0.20
    0.6%
    1403
    +0.14
    0.4%
    1284
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.20
    -0.00
    678
    +0.14
    0.04
    1284
    +0.13
    0.04
    Negative Logits
     kosme
    -0.87
     Demokrat
    -0.87
     bakteri
    -0.86
     kalori
    -0.82
     radikal
    -0.82
    Perú
    -0.81
     silikon
    -0.81
     kriminal
    -0.80
     akade
    -0.79
    Educación
    -0.79
    POSITIVE LOGITS
     scrat
    2.02
     eiffel
    2.00
     affor
    1.93
     increa
    1.92
     guarante
    1.91
     encomp
    1.87
     maneu
    1.86
     milf
    1.85
     lamborghini
    1.81
     squa
    1.81
    Activations Density 0.263%

    No Known Activations