© 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. 18-GEMMASCOPE-RES-16K
    11. 8440
    Prev
    Next
    INDEX
    Explanations

    phrases that involve expectations, context, and requests for clarifications or additional information

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

    Followed by terms of service/legal jargon

    np_acts-logits-general · gemini-2.0-flash

    your/our followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irs
    -0.47
     виду
    -0.46
     in
    -0.46
     to
    -0.45
     for
    -0.44
     peu
    -0.44
     make
    -0.44
     kind
    -0.44
     set
    -0.42
     last
    -0.42
    POSITIVE LOGITS
    IndentedString
    1.19
    tagHelperRunner
    1.18
     تضيفلها
    1.13
    IntoConstraints
    1.12
    IUrlHelper
    1.08
    ftagPool
    1.08
     المعيارى
    1.07
     betweenstory
    1.05
     gynhyrchwyd
    1.05
    ंदीखरीदारी
    1.03
    Activations Density 0.189%

    No Known Activations