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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 12836
    Prev
    Next
    INDEX
    Explanations

    references to concepts of identity and identity management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -1.17
     "..\..\..\
    -1.07
     ***!
    -1.02
    httphttps
    -0.99
    UAWEI
    -0.98
     שוליים
    -0.98
     Hawthorn
    -0.98
     propOrder
    -0.98
    SharedDtor
    -0.97
     дописавши
    -0.97
    POSITIVE LOGITS
     identity
    2.03
     Identity
    1.91
    Identity
    1.87
    identity
    1.67
     IDENTITY
    1.63
     identities
    1.61
    IDENTITY
    1.57
     Identities
    1.46
     identité
    1.24
     Identität
    1.24
    Activations Density 0.084%

    No Known Activations