© 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. 35-GEMMASCOPE-RES-16K
    6. 14322
    Prev
    Next
    INDEX
    Explanations

    phrases indicating future time frames or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    further
    -0.39
     snart
    -0.37
    <!--[
    -0.36
    })();
    
    -0.36
    SharedCtor
    -0.34
     Subsequently
    -0.34
    GTCX
    -0.34
     subsequently
    -0.34
     Anschließend
    -0.32
    当年
    -0.32
    POSITIVE LOGITS
     future
    2.02
     Future
    1.65
    future
    1.60
    Future
    1.59
     FUTURE
    1.53
     futuro
    1.45
     Zukunft
    1.43
     toekomst
    1.43
    FUTURE
    1.41
     futures
    1.36
    Activations Density 0.314%

    No Known Activations