© 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. 9637
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory and legal frameworks in various contexts

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

    preceding the purpose or reason for something

    np_acts-logits-general · gemini-2.0-flash

    for a purpose

    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
     for
    -0.84
    めでとう
    -0.66
     untuk
    -0.61
    for
    -0.59
    #+#
    -0.58
     برای
    -0.57
    })));
    -0.53
    對於
    -0.52
     för
    -0.52
     для
    -0.51
    POSITIVE LOGITS
     purposes
    1.56
    purposes
    1.20
     sake
    1.12
     Purposes
    1.05
     purpose
    0.97
    Purpose
    0.84
    purpose
    0.79
     Zwecke
    0.78
     reasons
    0.75
     Sake
    0.73
    Activations Density 0.644%

    No Known Activations