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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12758
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
    +0.22
    0.7%
    50
    +0.10
    0.3%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.22
    0.04
    1486
    +0.10
    0.03
    1900
    +0.10
    0.02
    Negative Logits
    <bos>
    -0.59
    Eksteraj
    -0.56
    aspectj
    -0.55
    hyrchwyd
    -0.54
    Zunanje
    -0.53
     Tweede
    -0.51
    ⓧ
    -0.50
     testar
    -0.49
    álbum
    -0.49
    ($__
    -0.48
    POSITIVE LOGITS
     embodi
    0.78
     fluo
    0.75
     applau
    0.72
     ciment
    0.71
     magis
    0.70
    !«
    0.69
     perche
    0.69
     haer
    0.68
     diph
    0.67
     bordeaux
    0.67
    Activations Density 0.096%

    No Known Activations