© 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. 2398
    Prev
    Next
    INDEX
    Explanations

    references to political motivations and actions related to power dynamics

    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
    604
    +0.16
    0.7%
    198
    +0.14
    0.6%
    50
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.12
    1325
    +0.14
    0.04
    1664
    +0.11
    0.04
    Negative Logits
    <bos>
    -3.68
    .
    -1.33
    ↵↵
    -1.10
    ↵
    -1.08
    ,
    -1.07
    ...
    -1.05
    。
    -1.03
    :
    -1.03
    ;
    -1.02
     
    -1.02
    POSITIVE LOGITS
     lidl
    2.65
     napoli
    2.41
     stockholm
    2.40
     milano
    2.39
     ibiza
    2.39
     ricardo
    2.34
     sergio
    2.32
     sappi
    2.31
     frankfurt
    2.30
     tramont
    2.29
    Activations Density 1.833%

    No Known Activations