© 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. 15-GEMMASCOPE-RES-16K
    11. 2647
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of stability or consistency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.52
     noten
    -0.52
    __'
    -0.49
     nonatomic
    -0.49
     gainera
    -0.49
    timewa
    -0.48
    jago
    -0.48
    urably
    -0.48
    ticularly
    -0.48
    Personensuche
    -0.47
    POSITIVE LOGITS
    ьаж
    0.63
     geblieben
    0.62
     vectorielle
    0.59
    ]")]
    0.59
     or
    0.56
     unchanging
    0.56
    trung
    0.56
     unchanged
    0.56
    AddTagHelper
    0.55
     parfaite
    0.55
    Activations Density 0.497%

    No Known Activations