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. 10136
    Prev
    Next
    INDEX
    Explanations

    facts and statistics related to military and civilian personnel from different countries

    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
    674
    +0.22
    0.7%
    1343
    +0.19
    0.6%
    453
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1900
    +0.22
    0.02
    1343
    +0.19
    0.03
    453
    +0.15
    0.03
    Negative Logits
     fta
    -1.08
     ftu
    -1.02
     madonna
    -1.01
     thut
    -1.01
     perfon
    -1.00
     fays
    -0.99
    <^
    -0.98
     ftre
    -0.97
     fup
    -0.96
     squa
    -0.95
    POSITIVE LOGITS
     snippetHide
    0.64
     poveznice
    0.61
    <eos>
    0.53
     guma
    0.50
    autique
    0.50
     onCancelled
    0.50
     pelig
    0.48
     intptr
    0.47
     end
    0.47
     <<<<<<<<<<<<<<
    0.45
    Activations Density 0.087%

    No Known Activations