© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    words related to financial transactions and physical objects like wine and wine descriptors

    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
    1.5%
    783
    +0.08
    0.4%
    184
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.34
    0.16
    1438
    +0.08
    0.09
    783
    +0.08
    0.10
    Negative Logits
    <bos>
    -3.10
    ⓧ
    -0.83
    GEBURTSDATUM
    -0.74
    Geplaatst
    -0.73
    Autoritní
    -0.69
    Билгалдахарш
    -0.67
    /**
    -0.67
    .
    -0.66
    ,
    -0.66
    EndGlobalSection
    -0.65
    POSITIVE LOGITS
     bandung
    1.41
     pymysql
    1.30
     maroc
    1.28
     lele
    1.27
     jawa
    1.25
     hcm
    1.25
     Minang
    1.24
     thuy
    1.23
     véhic
    1.22
     :)</
    1.21
    Activations Density 2.906%

    No Known Activations