© 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. 7239
    Prev
    Next
    INDEX
    Explanations

    references to particular individuals

    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
    1350
    +0.13
    0.5%
    1194
    +0.12
    0.4%
    1828
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1194
    +0.13
    0.06
    1919
    +0.12
    0.08
    1828
    +0.12
    0.07
    Negative Logits
     makro
    -1.34
     lele
    -1.31
     alkoh
    -1.24
     silikon
    -1.24
     kamb
    -1.23
     karton
    -1.22
     moza
    -1.19
     traktor
    -1.18
     kafe
    -1.18
     kask
    -1.17
    POSITIVE LOGITS
     who
    0.90
    who
    0.79
     whom
    0.78
     Who
    0.77
    Who
    0.73
     whose
    0.72
     quienes
    0.69
     WHO
    0.69
     którzy
    0.63
    whose
    0.62
    Activations Density 0.203%

    No Known Activations