© 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. 38-GEMMASCOPE-RES-16K
    6. 14811
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to NULL checking and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NegativeButton
    -0.51
     ProtoMessage
    -0.49
    ostomy
    -0.48
    abstractmethod
    -0.48
     oprot
    -0.48
    UnsafeEnabled
    -0.48
     Stare
    -0.46
    Derbyniad
    -0.45
    Depends
    -0.45
     Stored
    -0.45
    POSITIVE LOGITS
     syntax
    1.05
    syntax
    0.78
    语法
    0.77
    Syntax
    0.75
     Syntax
    0.74
     declaration
    0.72
     statements
    0.67
     declarations
    0.66
     statement
    0.63
     declaração
    0.63
    Activations Density 1.401%

    No Known Activations