© 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. 3550
    Prev
    Next
    INDEX
    Explanations

    out verbs related to understanding or realizing

    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
    0.7%
    78
    +0.08
    0.3%
    30
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.20
    0.05
    1056
    +0.08
    0.06
    733
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.81
    <?
    -1.12
    ⓧ
    -0.99
    
    -0.80
    /**
    -0.73
    <?
    -0.65
     shenan
    -0.62
     intersper
    -0.62
     cooperated
    -0.60
     mustered
    -0.59
    POSITIVE LOGITS
     meis
    1.03
     magis
    0.92
     alpes
    0.91
     thut
    0.90
     tomat
    0.90
     jawa
    0.90
     myn
    0.89
     vnd
    0.89
     lepro
    0.88
     lele
    0.88
    Activations Density 0.726%

    No Known Activations