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. 10081
    Prev
    Next
    INDEX
    Explanations

    technical terms related to chemistry and pharmacology

    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
    +0.15
    0.5%
    814
    +0.12
    0.4%
    976
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.15
    0.04
    382
    +0.12
    0.04
    1343
    +0.12
    0.04
    Negative Logits
    Czym
    -0.53
     Lair
    -0.52
    Więcej
    -0.51
     frivol
    -0.50
    sowie
    -0.50
    Gdzie
    -0.47
    loài
    -0.47
    spesies
    -0.46
    Materiał
    -0.46
    IUrlHelper
    -0.46
    POSITIVE LOGITS
     ananas
    1.02
     magis
    0.99
     meis
    0.99
     cæ
    0.98
     utop
    0.96
     habet
    0.95
     maxime
    0.92
     solidar
    0.92
     haer
    0.91
     Giugno
    0.91
    Activations Density 0.108%

    No Known Activations