© 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. 220
    Prev
    Next
    INDEX
    Explanations

    numerical values and specific dates mentioned in a text

    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
    50
    +0.14
    0.8%
    2019
    +0.04
    0.2%
    98
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.14
    0.17
    805
    +0.04
    0.18
    381
    +0.04
    -0.10
    Negative Logits
    <bos>
    -1.46
    ⓧ
    -1.07
    public
    -0.98
    </tbody>
    -0.94
    enumerate
    -0.94
    BUYER
    -0.94
    protected
    -0.91
    <eos>
    -0.90
     immer
    -0.90
    ുറ
    -0.90
    POSITIVE LOGITS
     maneu
    3.76
     affor
    3.66
     increa
    3.62
     impra
    3.40
     accla
    3.38
     strick
    3.32
     reluct
    3.32
     depic
    3.26
     shenan
    3.25
     guarante
    3.25
    Activations Density 10.222%

    No Known Activations