© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4047
    Prev
    Next
    INDEX
    Explanations

    repeated instances of a specific identifier or keyword related to a character or entity in a fictional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnitTesting
    -0.58
    AddTagHelper
    -0.47
     censiti
    -0.43
    Gambas
    -0.43
    copia
    -0.42
    discount
    -0.42
     Commencez
    -0.41
    ViewChild
    -0.41
    literals
    -0.40
    tricks
    -0.40
    POSITIVE LOGITS
    ga
    2.45
    GA
    1.89
     ga
    1.84
     GA
    1.57
    Ga
    1.56
     Ga
    1.52
    gaa
    0.98
    गा
    0.89
    га
    0.83
     GAZ
    0.79
    Activations Density 0.377%

    No Known Activations