© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 120
    Prev
    Next
    INDEX
    Explanations

    dates and news article metadata

    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
    200
    +0.10
    0.3%
    1053
    +0.08
    0.2%
    585
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.10
    0.02
    1343
    +0.08
    0.04
    724
    +0.07
    0.03
    Negative Logits
    vų
    -0.70
    HideFlags
    -0.66
     Shetterly
    -0.64
    çadas
    -0.64
    engeance
    -0.64
    éndole
    -0.63
     стаття
    -0.62
    Estou
    -0.60
    čiu
    -0.60
    Jornal
    -0.58
    POSITIVE LOGITS
    tos
    2.29
     affor
    1.83
     reluct
    1.79
     disagre
    1.79
     fuf
    1.75
     guarante
    1.72
     fup
    1.72
     maneu
    1.72
     ftu
    1.68
     increa
    1.67
    Activations Density 0.314%

    No Known Activations