© 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. 21-GEMMASCOPE-RES-16K
    11. 8059
    Prev
    Next
    INDEX
    Explanations

    greetings and conversational openings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sp
    -0.41
     mode
    -0.39
     fact
    -0.38
     not
    -0.38
     extra
    -0.36
     might
    -0.34
    తు
    -0.34
    不该
    -0.34
     stand
    -0.33
    osoba
    -0.33
    POSITIVE LOGITS
     hello
    2.44
     Hello
    2.39
    Hello
    2.28
    hello
    2.00
    Hi
    1.96
     Hi
    1.93
     HELLO
    1.81
     hi
    1.78
     Greetings
    1.75
    HELLO
    1.74
    Activations Density 0.212%

    No Known Activations