© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11286
    Prev
    Next
    INDEX
    Explanations

    references to information, security, and data flow in communication systems

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

    preceding "reaches" or similar verbs

    np_acts-logits-general · gemini-2.0-flash

    arrival or reaching a destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.61
    protoc
    -0.58
    principalColumn
    -0.53
    WebpackPlugin
    -0.53
    autoIncrement
    -0.52
    iredo
    -0.51
     rospy
    -0.51
    mids
    -0.51
    clusion
    -0.50
     Eink
    -0.47
    POSITIVE LOGITS
     arrive
    1.38
     arrives
    1.37
     arriving
    1.34
     arrived
    1.22
     reaching
    1.16
     reach
    1.08
     enters
    1.07
     reaches
    1.07
    Arri
    1.06
    arrive
    1.05
    Activations Density 0.894%

    No Known Activations