© 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. 6-RES-JB
    11. 5856
    Prev
    Next
    INDEX
    Explanations

    web links and technical information like website URLs and numerical data in a document

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    1.1%
    2019
    +0.12
    0.6%
    1343
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.04
    1343
    +0.12
    0.04
    1896
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.67
    ⓧ
    -1.24
    /**
    -1.20
     intersper
    -1.18
    
    -1.14
     quitted
    -0.94
    <?
    -0.92
     disbur
    -0.91
     forbear
    -0.89
     endow
    -0.88
    POSITIVE LOGITS
    Literat
    0.80
     marea
    0.77
     ados
    0.71
     corrom
    0.71
     psicologia
    0.70
     Pièces
    0.69
     Hauteur
    0.68
     lanterna
    0.66
    Glej
    0.66
    Sklici
    0.66
    Activations Density 0.128%

    No Known Activations