© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10706
    Prev
    Next
    INDEX
    Explanations

    concepts related to feedback and its impact on organizational culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.56
    ScopeManager
    -0.50
    RegressionTest
    -0.49
    InputBorder
    -0.45
     producciones
    -0.44
    empêcher
    -0.39
    TestingModule
    -0.38
    pgterms
    -0.37
     bandeira
    -0.36
    featureID
    -0.36
    POSITIVE LOGITS
     leveraged
    0.65
     LinkedIn
    0.62
     leveraging
    0.62
     leadership
    0.59
     CEOs
    0.58
     leverage
    0.55
     strategic
    0.55
    LinkedIn
    0.54
     CEO
    0.53
     estratégica
    0.51
    Activations Density 0.491%

    No Known Activations