© 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. 41-GEMMASCOPE-RES-16K
    6. 6872
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <>",
    -0.55
    Tracce
    -0.44
    tagHelperRunner
    -0.43
    StylePriority
    -0.42
    AppMethodBeat
    -0.39
    árbol
    -0.39
    queryInterface
    -0.39
    CharacterOffset
    -0.38
     Meksiku
    -0.38
     interpreted
    -0.38
    POSITIVE LOGITS
     subordinates
    0.54
     mind
    0.48
     mood
    0.47
     strength
    0.45
     thoughts
    0.44
    хьтан
    0.44
     cultivation
    0.42
     combat
    0.42
     merits
    0.41
     father
    0.40
    Activations Density 0.115%

    No Known Activations