© 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. 4002
    Prev
    Next
    INDEX
    Explanations

    phrases related to success and potential in various contexts

    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
    +0.33
    1.2%
    1108
    +0.09
    0.3%
    1438
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    792
    +0.33
    0.04
    1104
    +0.09
    0.04
    1081
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.54
    /***
    -0.62
    Autoritní
    -0.58
    posób
    -0.55
    <?
    -0.55
     and
    -0.55
     therefore
    -0.54
     endow
    -0.53
     modernize
    -0.53
     thus
    -0.52
    POSITIVE LOGITS
     wien
    1.19
     aen
    1.12
     ejus
    1.11
     nomine
    1.09
     maroc
    1.08
     meis
    1.08
     magis
    1.05
     nece
    1.02
     tamen
    1.01
     ridu
    1.01
    Activations Density 0.749%

    No Known Activations