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. 13659
    Prev
    Next
    INDEX
    Explanations

    indications of warnings, claims, and defenses related to trust and transparency in political discourse

    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
     say
    -0.48
    ptes
    -0.48
    仔
    -0.44
     done
    -0.41
     öğ
    -0.40
     řek
    -0.40
    !
    -0.40
     تر
    -0.40
     cabeça
    -0.39
     <
    -0.39
    POSITIVE LOGITS
    NUMX
    0.94
     يتيمه
    0.91
     gyhoeddwyd
    0.85
    :✨
    0.84
    ValueStyle
    0.82
    Personendaten
    0.81
     isInitialized
    0.79
    脚注の使い方
    0.78
    SharedDtor
    0.76
    awaiter
    0.76
    Activations Density 0.392%

    No Known Activations