© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1558
    Prev
    Next
    INDEX
    Explanations

    sentences expressing hope or anticipation

    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
    +0.07
    0.3%
    1178
    +0.07
    0.2%
    1757
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.07
    0.03
    1129
    +0.07
    0.03
    152
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.13
    public
    -0.71
    define
    -0.68
    
    -0.66
    #
    -0.65
    import
    -0.64
     do
    -0.63
    addComponent
    -0.63
    displayquote
    -0.63
    void
    -0.62
    POSITIVE LOGITS
     maneu
    2.04
     impra
    1.95
     stockholm
    1.85
     excru
    1.78
     increa
    1.78
     emphat
    1.76
     eiffel
    1.75
     affor
    1.71
     jurassic
    1.70
     pixar
    1.70
    Activations Density 0.076%

    No Known Activations