© 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. 7318
    Prev
    Next
    INDEX
    Explanations

    mentions of personal information and professional achievements

    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
    50
    +0.27
    1.2%
    2019
    +0.09
    0.4%
    908
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1539
    +0.27
    0.03
    908
    +0.09
    0.03
    1871
    +0.09
    0.03
    Negative Logits
    <bos>
    -3.27
    FunctionFlags
    -0.78
     AssemblyCompany
    -0.72
    ⓧ
    -0.66
    новништво
    -0.64
     ddelweddau
    -0.63
     jsPsych
    -0.63
    Personendaten
    -0.63
    contentLoaded
    -0.63
    InstrumentedTest
    -0.62
    POSITIVE LOGITS
     maroc
    1.24
     délib
    1.13
     déchir
    1.10
     épu
    1.09
     peugeot
    1.09
     olx
    1.07
     wien
    1.05
     milano
    1.02
     shopee
    1.02
     démoc
    1.01
    Activations Density 0.471%

    No Known Activations