© 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. 31-GEMMASCOPE-RES-16K
    6. 2774
    Prev
    Next
    INDEX
    Explanations

    references to social media and its related dynamics

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

    references to online platforms and digital services.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Garantía
    -0.44
     affrontare
    -0.36
    AutoScale
    -0.36
     trecut
    -0.36
    TestFixture
    -0.35
     richiesto
    -0.35
     passende
    -0.35
     reprinted
    -0.35
    antwoorden
    -0.34
    TagHelper
    -0.34
    POSITIVE LOGITS
     platform
    1.15
     platforms
    1.14
    platform
    0.99
     Platforms
    0.95
     plataforma
    0.94
     piattaforma
    0.93
    platforms
    0.88
     plataformas
    0.88
     Platform
    0.87
    平台
    0.87
    Activations Density 0.557%

    No Known Activations