© 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. 215
    Prev
    Next
    INDEX
    Explanations

    names and titles related to events or ceremonies, such as officiants, venues, and schedules

    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
    1044
    +0.10
    0.3%
    2000
    +0.10
    0.3%
    1328
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1044
    +0.10
    0.03
    1363
    +0.10
    0.03
    1343
    +0.10
    0.03
    Negative Logits
    <bos>
    -0.79
    vo
    -0.61
    باز
    -0.60
    Бі
    -0.57
    Alemania
    -0.57
     shouldn
    -0.56
     should
    -0.55
     ale
    -0.55
    export
    -0.54
    社
    -0.54
    POSITIVE LOGITS
    ord
    2.39
    ORD
    1.91
    ords
    1.84
     ordina
    1.83
     ord
    1.75
     ORD
    1.75
     Ord
    1.73
    Ord
    1.66
     CORD
    1.65
     Cord
    1.57
    Activations Density 0.205%

    No Known Activations