© 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. 14788
    Prev
    Next
    INDEX
    Explanations

    information about types and categories related to products or options

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

    "Each", "Some", "Many", or "Different"

    np_acts-logits-general · gemini-2.0-flash

    varying depending on type

    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
    AddTagHelper
    -0.84
    setupUi
    -0.78
    expandindo
    -0.78
    XmlAccessType
    -0.77
     ddelweddau
    -0.74
    دانشنامهٔ
    -0.68
    RectangleBorder
    -0.67
    ---*/
    -0.66
    ReusableCell
    -0.66
     '\\;'
    -0.65
    POSITIVE LOGITS
     each
    1.07
     depending
    1.06
     Each
    0.95
    Each
    0.94
    each
    0.91
    depending
    0.91
     different
    0.82
    Depending
    0.81
     Depending
    0.80
     depends
    0.80
    Activations Density 0.315%

    No Known Activations