© 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. 10-RES-JB
    11. 4549
    Prev
    Next
    INDEX
    Explanations

    words relating to limitations and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.28
    1.0%
    897
    +0.09
    0.3%
    198
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.28
    0.04
    420
    +0.09
    0.04
    897
    +0.08
    0.03
    Negative Logits
    <bos>
    -2.71
    AddAttribute
    -0.76
    WriteLiteral
    -0.75
    attr
    -0.75
    break
    -0.74
    let
    -0.73
    },{
    -0.73
    addPreferredGap
    -0.72
    add
    -0.72
    <tr>
    -0.70
    POSITIVE LOGITS
     hcm
    1.96
     maneu
    1.90
     Juf
    1.87
     embodi
    1.83
     scrat
    1.81
     swarovski
    1.78
     squa
    1.77
     affor
    1.75
     hairc
    1.74
     ecru
    1.74
    Activations Density 0.256%

    No Known Activations