© 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. 37-GEMMASCOPE-RES-16K
    6. 4251
    Prev
    Next
    INDEX
    Explanations

    terms related to personal experiences and reflections on past events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.43
    skjaer
    -0.38
    utenants
    -0.36
     inherent
    -0.35
    genöss
    -0.35
     apellidos
    -0.35
    protoimpl
    -0.35
     ſche
    -0.35
    ⊢
    -0.34
     sẵn
    -0.34
    POSITIVE LOGITS
     eventful
    1.30
     memorable
    1.09
     fruitful
    0.93
     tumultuous
    0.93
     unforgettable
    0.93
     productive
    0.89
     enjoyable
    0.86
     traumatic
    0.86
     stressful
    0.85
     bumpy
    0.82
    Activations Density 0.398%

    No Known Activations