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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 515
    Prev
    Next
    INDEX
    Explanations

    affirmations about positive attributes or blessings

    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%
    1967
    +0.08
    0.3%
    198
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.33
    0.07
    1415
    +0.08
    0.05
    1062
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.93
    AddAttribute
    -0.70
    ///**
    -0.67
    /***
    -0.66
    ComponentModel
    -0.65
    CreateIndex
    -0.65
     however
    -0.63
    titleMargin
    -0.62
    ,
    -0.61
    Linq
    -0.58
    POSITIVE LOGITS
     guarante
    1.62
     increa
    1.58
     reluct
    1.58
     affor
    1.57
     fortn
    1.55
     accla
    1.52
     impra
    1.52
     inev
    1.50
     disagre
    1.48
     ecru
    1.47
    Activations Density 0.603%

    No Known Activations