© 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. 28-GEMMASCOPE-RES-16K
    11. 4626
    Prev
    Next
    INDEX
    Explanations

    references to specific items or experiences, often emphasizing their qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "This" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    this specific item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.56
     Italijanski
    -0.56
     Италијани
    -0.53
     OFDb
    -0.48
    Personendaten
    -0.47
     Orrell
    -0.46
    nezeu
    -0.45
    
    -0.44
    цезда
    -0.43
     Livro
    -0.43
    POSITIVE LOGITS
     particular
    0.55
    webElementXpaths
    0.47
    particular
    0.46
    MarshalTo
    0.43
     particolare
    0.39
     PARTICULAR
    0.38
    complexContent
    0.38
    EDEFAULT
    0.37
    Particular
    0.36
     marginBottom
    0.36
    Activations Density 0.204%

    No Known Activations