© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 237
    Prev
    Next
    INDEX
    Explanations

    references to specific political figures and their actions

    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%
    2019
    +0.13
    0.5%
    604
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.20
    0.11
    2019
    +0.13
    0.09
    304
    +0.12
    0.01
    Negative Logits
    <bos>
    -2.44
    ⓧ
    -1.33
     intersper
    -1.31
    
    -1.21
     swarovski
    -1.20
    /***
    -1.18
    <?
    -1.14
     hairc
    -1.11
     forbear
    -1.08
     AMAZ
    -1.05
    POSITIVE LOGITS
     hermosos
    0.53
     cabina
    0.53
     Pfalz
    0.52
     Republica
    0.52
    UIColor
    0.51
    E
    0.51
    Xaml
    0.51
    CNN
    0.51
     Händ
    0.50
    H
    0.50
    Activations Density 0.647%

    No Known Activations