© 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. 356
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and software troubleshooting

    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
    0.5%
    375
    +0.07
    0.3%
    1013
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.12
    0.07
    1197
    +0.07
    0.05
    1665
    +0.07
    0.07
    Negative Logits
    <bos>
    -2.95
    
    -0.93
    /**
    -0.90
    Autoritní
    -0.86
    ⓧ
    -0.83
    <?
    -0.74
    /*
    -0.71
    /***
    -0.67
    ándor
    -0.65
    }],
    -0.65
    POSITIVE LOGITS
     meis
    2.01
     lele
    1.72
     kaos
    1.68
     ohr
    1.66
     franz
    1.63
     Kategor
    1.62
     kram
    1.61
     aen
    1.58
     mef
    1.58
     wien
    1.56
    Activations Density 1.353%

    No Known Activations