© 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. 745
    Prev
    Next
    INDEX
    Explanations

    mentions of 'pond'

    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
    1092
    +0.10
    0.3%
    553
    +0.09
    0.3%
    68
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.10
    0.02
    1174
    +0.09
    0.01
    1343
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.08
     переписи
    -0.70
    createQuery
    -0.68
     rowspan
    -0.68
     colspan
    -0.68
    、
    -0.65
     could
    -0.65
     remain
    -0.65
     enhance
    -0.65
     create
    -0.65
    POSITIVE LOGITS
     stockholm
    1.80
     fup
    1.80
     wien
    1.76
     aen
    1.75
     mef
    1.74
     Augu
    1.74
     hcm
    1.71
     fta
    1.69
     »>
    1.62
     Intere
    1.62
    Activations Density 0.163%

    No Known Activations