© 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. 6608
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to performance and material characteristics in scientific contexts

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

    preceding "determines/determine"

    np_acts-logits-general · gemini-2.0-flash

    determines or depends on

    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
    ChildScrollView
    -0.74
    UnusedPrivate
    -0.72
    AxisAlignment
    -0.71
    expandindo
    -0.69
    ArrowToggle
    -0.66
     Савезне
    -0.64
    ModelSerializer
    -0.61
     muualla
    -0.61
    enumii
    -0.59
    GOTREF
    -0.59
    POSITIVE LOGITS
     determines
    1.80
     determine
    1.53
     Determines
    1.42
     determining
    1.40
    determin
    1.40
     menentukan
    1.28
    determine
    1.25
     dictate
    1.22
     depends
    1.17
     détermin
    1.17
    Activations Density 0.891%

    No Known Activations