© 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. 734
    Prev
    Next
    INDEX
    Explanations

    mentions of events or occurrences that are culturally significant

    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
    637
    +0.09
    0.2%
    1360
    +0.07
    0.2%
    192
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.09
    0.01
    1360
    +0.07
    0.02
    1363
    +0.06
    0.02
    Negative Logits
    addContainerGap
    -0.64
     houdt
    -0.61
     demnach
    -0.54
    vų
    -0.52
     besluit
    -0.51
    ดาว
    -0.51
    ਾਨ
    -0.50
     look
    -0.50
    日閲覧
    -0.49
    glLoadIdentity
    -0.48
    POSITIVE LOGITS
    ring
    1.51
     saar
    1.36
     maksi
    1.22
     Suom
    1.18
     Ferdin
    1.16
     „,
    1.13
     Hæ
    1.12
     makro
    1.12
     Võ
    1.12
     Teks
    1.10
    Activations Density 0.253%

    No Known Activations