© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 9749
    Prev
    Next
    INDEX
    Explanations

    themes of existential struggle and self-reflection

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

    emotional or intense language expressing suffering, struggle, humiliation, or strong negative feelings.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mainly
    -0.44
     annul
    -0.43
     hauled
    -0.43
     явно
    -0.41
     تقری
    -0.41
     suspiciously
    -0.40
     mainly
    -0.40
     expressly
    -0.40
     fixing
    -0.39
    alloon
    -0.38
    POSITIVE LOGITS
    setVerticalGroup
    0.66
    sizeCache
    0.51
    Jîn
    0.50
     Савезне
    0.47
    GEBURTSDATUM
    0.45
    mergeFrom
    0.45
    MemoryWarning
    0.45
    Portály
    0.44
     Италијани
    0.44
     CreateTagHelper
    0.43
    Activations Density 0.079%

    No Known Activations