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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 517
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions that imply deep emotional or philosophical significance

    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
    +0.18
    0.9%
    478
    +0.17
    0.8%
    1872
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.18
    0.03
    869
    +0.17
    0.02
    1141
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.27
     negoti
    -0.82
     intersper
    -0.81
     ineffec
    -0.80
     apprehen
    -0.77
     allude
    -0.72
     encomp
    -0.69
     mustered
    -0.68
     harmonize
    -0.66
     inaugurate
    -0.65
    POSITIVE LOGITS
     soggior
    1.16
     dott
    1.08
     napoli
    1.05
     auguri
    1.04
     quoique
    1.03
     marea
    1.01
     mezza
    1.01
     papà
    1.00
     paradiso
    1.00
     divertimento
    1.00
    Activations Density 0.053%

    No Known Activations