© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2481
    Prev
    Next
    INDEX
    Explanations

    mentions of descending or descended

    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
    281
    +0.09
    0.3%
    1328
    +0.07
    0.2%
    1678
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.09
    0.01
    1793
    +0.07
    0.02
    1679
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.77
    HasAnnotation
    -0.68
    ArgumentParser
    -0.67
    FieldBuilder
    -0.65
    MemoryWarning
    -0.64
    UnusedPrivate
    -0.63
    дивиду
    -0.63
    RuleContext
    -0.63
    fromnode
    -0.62
    InvalidProtocol
    -0.61
    POSITIVE LOGITS
     descend
    2.28
     descending
    2.20
     descent
    2.18
     descended
    2.08
     descends
    2.08
     Descent
    2.01
     Desc
    1.93
    descent
    1.91
    descend
    1.77
    descending
    1.71
    Activations Density 0.135%

    No Known Activations