© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8254
    Prev
    Next
    INDEX
    Explanations

    chats or conversations, particularly greetings and expressions of kindness

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

    casual greetings and salutations in chat messages.

    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
    加坡
    -0.28
     des
    -0.25
     tartalomajánló
    -0.24
    vejec
    -0.24
    chnet
    -0.24
     لبنان
    -0.23
    因
    -0.23
     Ler
    -0.22
    anstalt
    -0.22
     tears
    -0.22
    POSITIVE LOGITS
     hello
    2.31
     Hello
    2.30
    Hello
    2.13
    hello
    1.88
     Greetings
    1.77
     HELLO
    1.75
    Greetings
    1.74
     greetings
    1.71
     Hi
    1.70
    HELLO
    1.68
    Activations Density 0.274%

    No Known Activations