© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 262
    Prev
    Next
    INDEX
    Explanations

    instances of the word "strike" with varying contexts related to labor disputes or military actions

    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
    299
    +0.07
    0.3%
    50
    +0.07
    0.3%
    1676
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1676
    +0.07
    0.06
    1385
    +0.07
    0.08
    1870
    +0.06
    0.00
    Negative Logits
    <bos>
    -1.43
    public
    -0.67
    ,
    -0.66
    /**
    -0.66
     in
    -0.65
            
    -0.65
     also
    -0.65
    protected
    -0.64
     held
    -0.64
    //
    -0.64
    POSITIVE LOGITS
     maneu
    1.90
     stockholm
    1.77
     affor
    1.75
     increa
    1.74
     impra
    1.65
     jorge
    1.64
     bandung
    1.62
     scrat
    1.59
     jaya
    1.58
     ricardo
    1.57
    Activations Density 1.228%

    No Known Activations