© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2806
    Prev
    Next
    INDEX
    Explanations

    conversations or reports about events and activities happening in different communities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    0.6%
    382
    +0.13
    0.4%
    1535
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.17
    0.08
    1535
    +0.13
    0.00
    2034
    +0.12
    0.06
    Negative Logits
     daquele
    -0.70
    engeance
    -0.70
     😭😭
    -0.69
    ///**
    -0.68
    ittoria
    -0.65
     REACTOR
    -0.65
    otheby
    -0.64
    YNAM
    -0.64
     naquele
    -0.61
     guangdong
    -0.60
    POSITIVE LOGITS
     ApiService
    0.81
     ErrorCode
    0.76
     UserData
    0.76
     KeyCode
    0.75
     useRouter
    0.74
     LoginForm
    0.73
     seksi
    0.73
     MainPage
    0.73
     Strukt
    0.70
     elektronik
    0.70
    Activations Density 0.261%

    No Known Activations