Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15665
    Prev
    Next
    INDEX
    Explanations

    terms related to authenticity and realism in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.56
    windowFixed
    -0.51
    TestingModule
    -0.48
    RegressionTest
    -0.47
     للمعارف
    -0.45
     ſta
    -0.45
     ſte
    -0.45
     myſelf
    -0.43
     ſche
    -0.43
    AnchorTagHelper
    -0.43
    POSITIVE LOGITS
     nakalista
    0.52
     authentic
    0.49
     natural
    0.44
     originalen
    0.44
     original
    0.43
    natural
    0.42
    realistic
    0.42
     originali
    0.42
     realistic
    0.42
     naturales
    0.40
    Activations Density 0.453%

    No Known Activations