© 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. 1268
    Prev
    Next
    INDEX
    Explanations

    phrases related to making sure something is done or provided

    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
    +0.11
    0.4%
    1539
    +0.05
    0.2%
    475
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.11
    0.06
    1665
    +0.05
    0.06
    184
    +0.05
    0.01
    Negative Logits
    <bos>
    -1.68
    ///**
    -0.79
    setClass
    -0.71
    thâu
    -0.68
    MarshalTo
    -0.68
    setDo
    -0.68
    msgTypes
    -0.67
    ുറ
    -0.66
    toHaveBeen
    -0.66
    public
    -0.65
    POSITIVE LOGITS
     accla
    1.66
     affor
    1.63
     maneu
    1.52
     impra
    1.50
     stockholm
    1.48
     increa
    1.45
     fuf
    1.44
     strick
    1.43
     emphat
    1.42
     casio
    1.41
    Activations Density 1.323%

    No Known Activations