© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2989
    Prev
    Next
    INDEX
    Explanations

    references to skills and skill development

    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
    +0.25
    1.5%
    1482
    +0.13
    0.8%
    1870
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.25
    0.03
    1256
    +0.13
    0.02
    1482
    +0.13
    0.02
    Negative Logits
    <bos>
    -2.71
    <tfoot>
    -0.65
    HasIndex
    -0.59
     mobilize
    -0.58
     synthesize
    -0.53
     modernize
    -0.53
    
    -0.53
     synchronize
    -0.52
     infuse
    -0.51
    República
    -0.50
    POSITIVE LOGITS
     skills
    1.26
     skill
    1.25
     Minang
    1.20
     Skill
    1.19
     bandung
    1.19
    skills
    1.18
     Skills
    1.15
    Skill
    1.15
    Skills
    1.12
    skill
    1.09
    Activations Density 0.037%

    No Known Activations