© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 760
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "sunny" in the text

    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
    1222
    +0.08
    0.3%
    1491
    +0.08
    0.3%
    805
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.08
    0.03
    342
    +0.08
    0.02
    1664
    +0.07
    0.02
    Negative Logits
    <tfoot>
    -0.64
    /*
    -0.62
    </tbody>
    -0.60
    displayquote
    -0.59
    enumerate
    -0.58
     onBackPressed
    -0.56
    ⓧ
    -0.55
     begin
    -0.55
    object
    -0.54
     have
    -0.54
    POSITIVE LOGITS
     sunny
    2.20
    sunny
    2.00
     Sunny
    1.95
    Sunny
    1.88
     sunshine
    1.88
     Sunshine
    1.59
    sunshine
    1.53
    Sunshine
    1.52
     Sunlight
    1.32
     maneu
    1.28
    Activations Density 0.154%

    No Known Activations