© 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. 556
    Prev
    Next
    INDEX
    Explanations

    concepts related to societal power dynamics and resource management

    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
    1.1%
    1438
    +0.14
    0.6%
    2034
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.25
    0.10
    284
    +0.14
    0.09
    1385
    +0.11
    0.10
    Negative Logits
    <bos>
    -2.57
     intersper
    -1.46
     encomp
    -1.18
     endow
    -1.08
     reluct
    -1.08
     depic
    -1.03
     excru
    -1.02
     shenan
    -1.01
     circums
    -0.98
     inconce
    -0.97
    POSITIVE LOGITS
     kade
    0.88
     maske
    0.87
     optik
    0.82
     sfera
    0.79
     kafe
    0.77
     torba
    0.76
    abancı
    0.75
     kaos
    0.75
     geniales
    0.74
     IndexError
    0.74
    Activations Density 0.988%

    No Known Activations