© 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. 1179
    Prev
    Next
    INDEX
    Explanations

    contact details and privacy information on a website

    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
    +0.34
    2.3%
    1334
    +0.14
    0.9%
    161
    +0.10
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.34
    0.18
    161
    +0.14
    0.13
    395
    +0.10
    0.11
    Negative Logits
    <bos>
    -3.55
    /**
    -0.96
    ⓧ
    -0.94
    <?
    -0.92
    
    -0.73
    /*
    -0.70
    SharedCtor
    -0.65
     AssemblyCompany
    -0.65
    bootstrapcdn
    -0.64
    BeginInit
    -0.63
    POSITIVE LOGITS
     impra
    1.42
     maneu
    1.37
     reluct
    1.34
     affor
    1.30
     lamborghini
    1.28
     wikihow
    1.26
     increa
    1.25
     unlaw
    1.24
     disagre
    1.21
     accla
    1.20
    Activations Density 1.199%

    No Known Activations