© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4052
    Prev
    Next
    INDEX
    Explanations

    actions or commands related to obtaining, providing, or calculating information

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

    "get a" or "getting a"

    np_acts-logits-general · gemini-2.0-flash

    getting a or an

    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
    تقاوى
    -0.96
     resourceCulture
    -0.93
     surla
    -0.89
     '\\;'
    -0.83
     itſelf
    -0.81
     betweenstory
    -0.80
     snippetHide
    -0.77
    expandindo
    -0.70
     CreateTagHelper
    -0.65
     myſelf
    -0.64
    POSITIVE LOGITS
     a
    0.84
     either
    0.78
     plenty
    0.74
    的是
    0.73
     mostly
    0.72
     lots
    0.72
     an
    0.67
     some
    0.66
    的就是
    0.65
     nothing
    0.65
    Activations Density 0.381%

    No Known Activations