© 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. 6-RES-JB
    11. 4518
    Prev
    Next
    INDEX
    Explanations

    texts related to genres and categories

    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
    1059
    +0.17
    0.8%
    201
    +0.15
    0.7%
    90
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.17
    0.02
    1059
    +0.15
    0.02
    201
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.40
    /*
    -0.76
    migrationBuilder
    -0.73
    /**
    -0.62
    ⓧ
    -0.61
    estimable
    -0.59
    HideFlags
    -0.58
    
    -0.54
     jette
    -0.53
    ///**
    -0.53
    POSITIVE LOGITS
     genre
    1.40
     Genre
    1.25
    genre
    1.24
     genres
    1.17
    Genre
    1.14
     Genres
    1.10
    genres
    1.02
    Genres
    0.88
     reluct
    0.86
     tanong
    0.85
    Activations Density 0.237%

    No Known Activations