© 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. 189
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "duck" in different contexts

    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
    1328
    +0.11
    0.3%
    1479
    +0.08
    0.3%
    795
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.11
    0.02
    2044
    +0.08
    0.02
    1479
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.82
    VIAF
    -0.75
    WarningLevel
    -0.75
    HasIndex
    -0.64
     بتاريخ
    -0.62
     wireType
    -0.62
    로그램
    -0.62
    لينكات
    -0.61
    盛
    -0.61
    ാ
    -0.61
    POSITIVE LOGITS
     duck
    2.41
     Duck
    2.32
    duck
    2.16
    Duck
    2.06
     ducks
    2.00
     Ducks
    1.88
    ducks
    1.72
    Ducks
    1.61
     accla
    1.58
     reluct
    1.55
    Activations Density 0.167%

    No Known Activations