© 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. 10-RES-JB
    11. 3415
    Prev
    Next
    INDEX
    Explanations

    terms related to maritime and aerospace industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.27
    1.2%
    478
    +0.17
    0.8%
    50
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.27
    0.05
    1385
    +0.17
    0.06
    1233
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.25
    <?
    -0.80
    ⓧ
    -0.79
    /**
    -0.76
    <?
    -0.66
     geograph
    -0.63
    RepeatedField
    -0.63
     inaugurate
    -0.62
    EndInit
    -0.62
     fiduci
    -0.62
    POSITIVE LOGITS
     bandung
    0.95
     Ottobre
    0.93
     Giugno
    0.92
     Luglio
    0.91
     Février
    0.90
     jaya
    0.89
     Traité
    0.89
     marea
    0.83
     miniatura
    0.82
     cuit
    0.82
    Activations Density 0.235%

    No Known Activations