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. 1425
    Prev
    Next
    INDEX
    Explanations

    numerical data related to computing benchmarks and performance

    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
    +0.30
    0.9%
    690
    +0.13
    0.4%
    1699
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.30
    -0.01
    690
    +0.13
    0.02
    1834
    +0.10
    0.03
    Negative Logits
    <bos>
    -0.91
     Palestina
    -0.78
     Independencia
    -0.78
    Biografi
    -0.77
    Créditos
    -0.77
     Juventud
    -0.76
    Antecedentes
    -0.75
    Palmar
    -0.75
    Biografía
    -0.74
    Fotografía
    -0.73
    POSITIVE LOGITS
     impra
    1.77
     increa
    1.76
     maneu
    1.72
     disreg
    1.71
     encomp
    1.68
     shenan
    1.65
     impractica
    1.63
     scrat
    1.62
     depic
    1.61
     intermitt
    1.61
    Activations Density 0.351%

    No Known Activations