© 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. 76
    Prev
    Next
    INDEX
    Explanations

    references to Marvel characters or merchandise

    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
    486
    +0.10
    0.3%
    47
    +0.09
    0.3%
    971
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.03
    1793
    +0.09
    0.02
    570
    +0.08
    0.02
    Negative Logits
    
    -1.34
    ⓧ
    -1.27
    <bos>
    -1.25
    /**
    -1.22
     quitted
    -1.09
    <?
    -1.08
     pegasus
    -0.89
     intersper
    -0.87
     shenan
    -0.86
     gaily
    -0.84
    POSITIVE LOGITS
     Marvel
    1.97
    Marvel
    1.82
     Spider
    1.48
    Spider
    1.40
    marvel
    1.28
     spider
    1.18
     Avengers
    1.07
    spider
    1.06
     marvel
    1.05
    Avengers
    1.02
    Activations Density 0.159%

    No Known Activations