© 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. 0-RES-JB
    11. 94
    Prev
    Next
    INDEX
    Explanations

    names of a person, specifically "Kenny"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    313
    +0.10
    0.3%
    1618
    +0.10
    0.3%
    341
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.06
    1120
    +0.10
    0.05
    690
    +0.10
    0.05
    Negative Logits
     awakeFromNib
    -0.61
    AddHtmlAttribute
    -0.60
    strophe
    -0.59
     HÀ
    -0.59
    guang
    -0.57
     \%$\\
    -0.53
    ATILE
    -0.53
     andato
    -0.53
    lillah
    -0.53
    subaru
    -0.51
    POSITIVE LOGITS
     Kenny
    1.35
    Kenny
    1.20
     quoique
    1.13
     pavillon
    1.06
     Intere
    1.01
     vété
    1.00
     nephe
    1.00
     créateur
    0.99
     spécialisé
    0.97
     ux
    0.96
    Activations Density 0.302%

    No Known Activations