© 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. 31-GEMMASCOPE-RES-16K
    6. 630
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the process of acquiring or understanding something

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

    phrases where "get" is used as an auxiliary verb to describe a process or state change becoming more intense or complicated.

    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
     AssemblyTitle
    -0.65
    ########.
    -0.56
    ChildScrollView
    -0.55
     useAppContext
    -0.52
    ValueStyle
    -0.52
    OGND
    -0.50
     QtWidgets
    -0.50
    reportWebVitals
    -0.50
    MigrationBuilder
    -0.49
     informée
    -0.48
    POSITIVE LOGITS
     misused
    0.51
     hotter
    0.49
     worse
    0.45
     misinterpreted
    0.45
     tiresome
    0.45
     subtracted
    0.45
     overlooked
    0.45
    摆
    0.45
     lodged
    0.44
     darker
    0.43
    Activations Density 0.090%

    No Known Activations