© 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. 161
    Prev
    Next
    INDEX
    Explanations

    names that end with 'ky'

    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
    1491
    +0.08
    0.2%
    1350
    +0.07
    0.2%
    397
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.08
    0.03
    85
    +0.07
    0.02
    99
    +0.07
    0.02
    Negative Logits
     remain
    -0.64
    toMatch
    -0.64
     later
    -0.62
    <tfoot>
    -0.62
    unit
    -0.62
    站
    -0.61
    PRWEB
    -0.61
     we
    -0.60
     draw
    -0.60
    }{||
    -0.59
    POSITIVE LOGITS
    ky
    2.66
     wherea
    1.79
     accla
    1.75
     emphat
    1.75
    KY
    1.74
     secon
    1.73
     volunte
    1.67
     depic
    1.66
     Intere
    1.66
     squa
    1.65
    Activations Density 0.163%

    No Known Activations