© 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. 1024
    Prev
    Next
    INDEX
    Explanations

    words related to celebrations and well-wishes

    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
    50
    +0.07
    0.2%
    1506
    +0.07
    0.2%
    397
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.07
    0.02
    1896
    +0.07
    0.02
    1026
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.18
    char
    -0.88
     immer
    -0.84
     immediately
    -0.83
    ,
    -0.82
    .
    -0.82
    非
    -0.82
     together
    -0.81
     during
    -0.81
     again
    -0.80
    POSITIVE LOGITS
     affor
    2.76
     increa
    2.75
     maneu
    2.72
     strick
    2.71
     reluct
    2.62
     scrat
    2.61
     shenan
    2.60
     volunte
    2.60
     snoopy
    2.57
     philanth
    2.56
    Activations Density 0.237%

    No Known Activations