© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 807
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions, specifically highlighting Cambridge University

    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
    1983
    +0.08
    0.3%
    1506
    +0.07
    0.3%
    645
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1915
    +0.08
    0.02
    1120
    +0.07
    0.03
    1273
    +0.07
    0.02
    Negative Logits
     once
    -0.89
    addComponent
    -0.86
    setDo
    -0.85
    LayoutStyle
    -0.85
    void
    -0.84
    안
    -0.83
    Màu
    -0.83
    HasKey
    -0.83
    Đối
    -0.83
    HasOne
    -0.82
    POSITIVE LOGITS
     increa
    3.27
     inev
    3.19
     affor
    3.15
     guarante
    3.06
     maneu
    3.05
     effe
    2.96
     fuf
    2.85
     wherea
    2.85
     strick
    2.85
     alre
    2.84
    Activations Density 0.147%

    No Known Activations