© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs that suggest agency or responsibility

    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
    +0.29
    1.1%
    1416
    +0.10
    0.4%
    239
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1350
    +0.29
    0.03
    1610
    +0.10
    0.02
    12
    +0.08
    0.02
    Negative Logits
    <bos>
    -2.31
    <?
    -0.53
    conse
    -0.49
    url
    -0.47
     harmonize
    -0.46
    module
    -0.46
     AssemblyCompany
    -0.46
    ManyToMany
    -0.45
    /**
    -0.44
    },{
    -0.43
    POSITIVE LOGITS
     Muhamma
    0.88
     Jambi
    0.86
     Karang
    0.85
     jawa
    0.82
     Minang
    0.81
     Batam
    0.81
     sappi
    0.81
     tucson
    0.78
     jaya
    0.76
     dott
    0.73
    Activations Density 0.158%

    No Known Activations