© 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. 14342
    Prev
    Next
    INDEX
    Explanations

    mentions of locations such as universities, concerts, and the White House

    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
    1741
    +0.27
    0.9%
    1967
    +0.17
    0.6%
    50
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.27
    0.05
    16
    +0.17
    0.06
    368
    +0.11
    0.04
    Negative Logits
    ophosph
    -0.66
     couteau
    -0.65
     soeur
    -0.64
     gardien
    -0.62
     keineswegs
    -0.61
    APPY
    -0.61
     mwenye
    -0.60
     vielmehr
    -0.60
     $_[
    -0.59
     Şi
    -0.59
    POSITIVE LOGITS
     ideolog
    0.94
     solidar
    0.90
     robus
    0.75
     dici
    0.73
     cosi
    0.72
     monaster
    0.69
     traged
    0.69
     tenden
    0.69
     peculi
    0.68
     polig
    0.68
    Activations Density 0.314%

    No Known Activations