© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in discussions or events

    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
    50
    +0.20
    0.8%
    1150
    +0.19
    0.7%
    227
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.20
    0.07
    227
    +0.19
    0.06
    1150
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.43
     intersper
    -1.40
     dispen
    -1.25
     fuf
    -1.24
     embra
    -1.23
     desir
    -1.22
    ⓧ
    -1.16
     unden
    -1.15
    /***
    -1.15
     swarovski
    -1.14
    POSITIVE LOGITS
    .
    0.71
    cassert
    0.61
    ;
    0.59
    abancı
    0.59
     Integrals
    0.59
    ).
    0.58
     pylab
    0.58
    ]=="
    0.57
    cupertino
    0.56
    :
    0.55
    Activations Density 0.244%

    No Known Activations