© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 5444
    Prev
    Next
    INDEX
    Explanations

    phrases and structures that indicate contrast or complexity in a discussion

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

    Followed by adjectives

    np_acts-logits-general · gemini-2.0-flash

    linking descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     centralization
    -0.64
    induced
    -0.63
     tightness
    -0.61
     facilité
    -0.58
     sqlSession
    -0.55
    Induced
    -0.55
     consiguiente
    -0.54
     mici
    -0.52
     tangents
    -0.52
     CreateTagHelper
    -0.52
    POSITIVE LOGITS
     self
    0.66
    CrossRef
    0.64
     enough
    0.61
     highly
    0.60
     consultato
    0.59
     subject
    0.59
    DateField
    0.58
    BeginContext
    0.56
     very
    0.56
    expandindo
    0.56
    Activations Density 0.253%

    No Known Activations