© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    text that discusses learning, knowledge exchange, and historical information

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

    Following "learn," "read," or "knowledge"

    np_acts-logits-general · gemini-2.0-flash

    learning and information

    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
    FormTagHelper
    -0.55
    AndEndTag
    -0.53
    رشف
    -0.51
    ̀nh
    -0.51
     AssemblyCulture
    -0.50
    เร็
    -0.50
    IUrlHelper
    -0.49
    OrWhiteSpace
    -0.49
    PasswordField
    -0.48
     useRef
    -0.48
    POSITIVE LOGITS
     informative
    1.18
     information
    1.15
     informational
    1.14
    information
    1.08
     getInfo
    1.05
     learn
    1.04
     knowledge
    1.04
     info
    1.01
    knowledge
    0.99
     knowled
    0.97
    Activations Density 0.211%

    No Known Activations