© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 806
    Prev
    Next
    INDEX
    Explanations

    phrases expressing conditional statements regarding life and death choices in the context of family relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iſt
    -0.75
     Chaldean
    -0.72
     Theſe
    -0.71
     ſche
    -0.70
     reafon
    -0.69
    tagHelperRunner
    -0.68
     dialects
    -0.67
     $_"
    -0.67
    ISupport
    -0.67
    PasswordEncoder
    -0.66
    POSITIVE LOGITS
    Пусть
    0.56
     nantinya
    0.54
     laten
    0.53
     viewDidLoad
    0.52
     PartialEq
    0.50
     want
    0.50
     Пусть
    0.49
     be
    0.47
     salt
    0.46
     ‘
    0.45
    Activations Density 0.164%

    No Known Activations