© 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. 7259
    Prev
    Next
    INDEX
    Explanations

    references to political activism and government advocacy

    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
    1967
    +0.16
    0.5%
    1842
    +0.14
    0.5%
    1978
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.16
    0.08
    184
    +0.14
    0.03
    1967
    +0.13
    0.04
    Negative Logits
     increa
    -2.39
     impra
    -2.30
     stockholm
    -2.20
     guarante
    -2.18
     affor
    -2.15
     maneu
    -2.15
     perfet
    -2.15
     Juf
    -2.12
     disagre
    -2.10
     inev
    -2.07
    POSITIVE LOGITS
     really
    0.95
    .”
    0.92
    ."
    0.91
     maybe
    0.88
     [
    0.86
     actually
    0.86
     yeah
    0.80
    ,”
    0.79
    。”
    0.79
     things
    0.79
    Activations Density 0.618%

    No Known Activations