© 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. 893
    Prev
    Next
    INDEX
    Explanations

    actions related to changes, settings, installation, and disablement

    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
    +0.09
    0.4%
    876
    +0.07
    0.3%
    982
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.09
    0.07
    2044
    +0.07
    0.07
    184
    +0.06
    0.01
    Negative Logits
    <bos>
    -1.08
    /***
    -0.70
    public
    -0.70
    //{
    -0.64
    displayquote
    -0.61
    /**
    -0.58
    </tbody>
    -0.57
    <0xF0>
    -0.56
    Globalization
    -0.55
    ///**
    -0.55
    POSITIVE LOGITS
     marseille
    1.33
     bandung
    1.29
     maroc
    1.27
     milano
    1.26
     riviera
    1.24
     wien
    1.21
     papà
    1.20
     stockholm
    1.20
     frankfurt
    1.20
     napoli
    1.17
    Activations Density 0.812%

    No Known Activations