© 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. 24-GEMMASCOPE-RES-16K
    11. 4132
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to missing someone or longing for connection

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

    "miss" or "Miss"

    np_acts-logits-general · gemini-2.0-flash

    haven't or not missing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.62
    providedIn
    -0.61
     وتسجيلات
    -0.59
     الحره
    -0.56
     rospy
    -0.55
     '\\;'
    -0.55
     kaarangay
    -0.54
     protoimpl
    -0.53
    
    -0.52
    PostInfinity
    -0.51
    POSITIVE LOGITS
     miss
    3.05
     misses
    2.88
    miss
    2.58
     missed
    2.55
     MISS
    2.37
    Miss
    2.17
     missing
    2.17
     Miss
    2.12
     Missed
    2.04
    missed
    2.03
    Activations Density 0.170%

    No Known Activations