© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14403
    Prev
    Next
    INDEX
    Explanations

    numerical references such as dates, model numbers, or proper nouns

    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
    1177
    +0.20
    0.6%
    1741
    +0.14
    0.4%
    283
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1177
    +0.20
    0.07
    981
    +0.14
    0.11
    283
    +0.10
    0.01
    Negative Logits
      
    -1.10
    .
    -1.03
    -1.03
    ↵
    -1.01
        
    -1.00
     no
    -0.99
       
    -0.99
     in
    -0.98
     -
    -0.97
    ↵↵
    -0.97
    POSITIVE LOGITS
     emphat
    3.17
     accla
    3.07
     fta
    3.04
     embra
    3.03
     Mlle
    2.99
     wien
    2.98
     casio
    2.98
     inev
    2.97
     stockholm
    2.97
     strick
    2.96
    Activations Density 0.909%

    No Known Activations