© 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. 3017
    Prev
    Next
    INDEX
    Explanations

    terms related to frequency of reports or measurements, particularly those using "annual" or other time-related prefixes

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

    preceding units of time

    np_acts-logits-general · gemini-2.0-flash

    annual, daily, monthly measurements

    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
     annually
    -0.63
     sehari
    -0.62
     every
    -0.53
     actualmente
    -0.52
     diariamente
    -0.52
    vaadin
    -0.48
     everyday
    -0.48
     segü
    -0.48
    ecore
    -0.47
    every
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.86
     betweenstory
    0.84
    FontOfSize
    0.78
    Bref
    0.74
    AddTagHelper
    0.73
    ized
    0.73
    Autoritní
    0.71
     웹툰
    0.70
    InvalidProtocol
    0.69
    XmlEnum
    0.69
    Activations Density 0.075%

    No Known Activations