© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 843
    Prev
    Next
    INDEX
    Explanations

    pronouns such as "thou," "thee," and "thy" used in religious or formal contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    411
    +0.10
    0.3%
    528
    +0.07
    0.2%
    1942
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.10
    0.02
    1896
    +0.07
    0.01
    411
    +0.07
    0.02
    Negative Logits
     makro
    -1.18
     elek
    -1.14
     gero
    -1.11
     spek
    -1.06
     hek
    -1.03
     behar
    -1.01
     truk
    -0.98
     bera
    -0.97
     akus
    -0.97
     plak
    -0.92
    POSITIVE LOGITS
     thou
    2.41
     Thou
    2.30
    Thou
    2.06
     swarovski
    1.67
     ibiza
    1.66
     tucson
    1.63
    thou
    1.60
     ecru
    1.59
     thine
    1.56
     toledo
    1.55
    Activations Density 0.246%

    No Known Activations