© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2480
    Prev
    Next
    INDEX
    Explanations

    phrases that express political opinions or critiques

    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
    +0.17
    0.7%
    872
    +0.16
    0.6%
    1253
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.17
    0.09
    623
    +0.16
    0.05
    617
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.48
     intersper
    -1.11
     inaugurate
    -0.90
     amass
    -0.87
     endow
    -0.85
     acquaint
    -0.83
     indoc
    -0.81
     disambigu
    -0.80
     standardize
    -0.78
     punctu
    -0.77
    POSITIVE LOGITS
     împre
    1.00
     heapq
    0.96
     soste
    0.86
     signora
    0.85
    cluye
    0.85
     thuy
    0.84
    jinal
    0.83
     venuto
    0.83
     ados
    0.82
     pymysql
    0.82
    Activations Density 0.668%

    No Known Activations