© 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. 6-RES-JB
    11. 7090
    Prev
    Next
    INDEX
    Explanations

    technical specifications or specific details mentioned in content

    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
    +0.20
    1.1%
    893
    +0.12
    0.7%
    32
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    893
    +0.20
    0.03
    1994
    +0.12
    0.03
    1265
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.13
    /***
    -1.00
    /*!
    -0.75
    ///**
    -0.72
     endow
    -0.66
    Autoritní
    -0.64
     consolidate
    -0.63
     ratify
    -0.62
    #![
    -0.61
     inaugurate
    -0.61
    POSITIVE LOGITS
     bandung
    1.10
     pymysql
    1.07
     particolar
    1.04
     javier
    1.01
     useRouter
    1.00
     felipe
    0.98
     santiago
    0.98
     lidl
    0.96
     particular
    0.95
     tramont
    0.95
    Activations Density 0.056%

    No Known Activations