© 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. 502
    Prev
    Next
    INDEX
    Explanations

    statements about choice and autonomy, particularly regarding religious beliefs in children

    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
    +0.34
    1.7%
    382
    +0.20
    1.0%
    2034
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.34
    0.20
    2034
    +0.20
    0.18
    752
    +0.15
    0.12
    Negative Logits
    <bos>
    -2.92
    /**
    -1.13
    ⓧ
    -0.98
     intersper
    -0.98
    ///**
    -0.93
     gratify
    -0.92
    /***
    -0.86
     endow
    -0.85
     forbear
    -0.84
    <?
    -0.81
    POSITIVE LOGITS
     maksi
    0.74
     moza
    0.73
     ferie
    0.72
     marea
    0.70
     materie
    0.69
     karton
    0.66
     saad
    0.66
     épu
    0.66
    plak
    0.66
     expédi
    0.65
    Activations Density 1.169%

    No Known Activations