© 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. 592
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and the impact of parental influence

    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
    1.1%
    964
    +0.11
    0.4%
    1533
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.28
    0.04
    509
    +0.11
    0.07
    1948
    +0.10
    0.05
    Negative Logits
    <bos>
    -1.65
     intersper
    -1.43
     encomp
    -1.17
     gild
    -0.96
     disambigu
    -0.95
     inappro
    -0.92
     depic
    -0.92
     endow
    -0.90
     infinites
    -0.89
     indestru
    -0.88
    POSITIVE LOGITS
     famiglia
    0.67
     ComVisible
    0.63
     parenting
    0.62
     Señora
    0.61
    illères
    0.61
     familie
    0.61
     family
    0.60
     parental
    0.60
     jScrollPane
    0.60
     parents
    0.60
    Activations Density 0.755%

    No Known Activations