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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1921
    Prev
    Next
    INDEX
    Explanations

    technical terms regarding products and services

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    172
    +0.23
    1.4%
    874
    +0.19
    1.1%
    1404
    +0.18
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.23
    0.04
    783
    +0.19
    0.06
    172
    +0.18
    0.06
    Negative Logits
    <bos>
    -1.68
    yaitu
    -0.68
    casal
    -0.68
    Semoga
    -0.67
    secara
    -0.64
    дивиду
    -0.64
    Примеча
    -0.61
    /*!
    -0.61
    strona
    -0.60
    Lma
    -0.60
    POSITIVE LOGITS
     jaya
    1.31
     lele
    1.29
     sii
    1.21
     bandung
    1.19
     seksi
    1.11
     jati
    1.10
     alip
    1.09
     vnt
    1.08
     kasa
    1.08
     hina
    1.08
    Activations Density 1.018%

    No Known Activations