© 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. 717
    Prev
    Next
    INDEX
    Explanations

    mentions of building, construction, or development activities specified in a technical or architectural context

    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
    +0.12
    0.6%
    1103
    +0.06
    0.3%
    341
    +0.05
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    164
    +0.12
    0.05
    930
    +0.06
    0.05
    1634
    +0.05
    0.05
    Negative Logits
    <bos>
    -1.57
    public
    -0.71
    hline
    -0.68
    ,
    -0.68
    //
    -0.67
    ുറ
    -0.65
    /**
    -0.65
    /**
    -0.65
    ///
    -0.65
    .
    -0.65
    POSITIVE LOGITS
     affor
    2.17
     maneu
    2.17
     increa
    2.08
     impra
    2.03
     accla
    1.96
     inev
    1.87
     disagre
    1.87
     buil
    1.86
     emphat
    1.85
     stockholm
    1.83
    Activations Density 0.090%

    No Known Activations