© 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. 18-GEMMASCOPE-RES-16K
    11. 2914
    Prev
    Next
    INDEX
    Explanations

    transitional and conclusive phrases that indicate change or progression in a narrative

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

    preceding a verb of consequence

    np_acts-logits-general · gemini-2.0-flash

    concluding outcomes and findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.79
    providedIn
    -0.69
    Hentet
    -0.69
     émotion
    -0.59
     sicuramente
    -0.58
    træ
    -0.57
    certainly
    -0.56
    estacks
    -0.56
     yder
    -0.55
    (;;)
    -0.55
    POSITIVE LOGITS
    RegistryLite
    0.97
    eens
    0.62
     unknownFields
    0.60
     تضيفلها
    0.57
    TargetException
    0.57
     оригіналу
    0.57
    ly
    0.56
    izada
    0.55
    arily
    0.55
    csak
    0.55
    Activations Density 0.774%

    No Known Activations