© 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. 4389
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate offering or presenting information and insights

    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
    1.3%
    1515
    +0.10
    0.4%
    849
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1110
    +0.33
    0.03
    240
    +0.10
    0.03
    1356
    +0.09
    0.03
    Negative Logits
    <bos>
    -1.58
     intersper
    -1.26
     encomp
    -1.17
     indestru
    -1.14
     quitted
    -1.06
     apprehen
    -1.04
     disagre
    -1.04
     shenan
    -1.03
     reluct
    -1.02
     Shakspeare
    -1.01
    POSITIVE LOGITS
     intrig
    0.72
     paradigma
    0.68
    hoea
    0.67
     Provides
    0.67
     tinte
    0.67
     opportunity
    0.65
    Provides
    0.65
     minori
    0.62
     utop
    0.61
     gatti
    0.61
    Activations Density 0.251%

    No Known Activations