© 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. 272
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific context or narrative, perhaps related to gaming or technology

    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
    +0.16
    0.9%
    122
    +0.06
    0.3%
    47
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.16
    0.07
    122
    +0.06
    0.06
    416
    +0.06
    0.06
    Negative Logits
    <bos>
    -2.35
    public
    -0.79
    ⓧ
    -0.76
    <?
    -0.76
    //
    -0.73
    ोंने
    -0.73
    /**
    -0.72
    
    -0.70
    ///
    -0.69
    ,
    -0.69
    POSITIVE LOGITS
     stockholm
    1.66
     maneu
    1.60
     accla
    1.57
     fta
    1.56
     affor
    1.55
     Juf
    1.55
     increa
    1.55
     viciss
    1.53
     effe
    1.52
     ftu
    1.52
    Activations Density 0.085%

    No Known Activations