© 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. 16-GEMMASCOPE-RES-16K
    11. 4053
    Prev
    Next
    INDEX
    Explanations

    phrases or elements related to reporting and procedure details

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

    Punctuation followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    recently sometimes often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.67
    
    -0.64
    RTEX
    -0.57
     Signalez
    -0.56
    MigrationBuilder
    -0.56
    featureID
    -0.55
    ArrowToggle
    -0.53
    DataAnnotations
    -0.53
    وفاته
    -0.52
    IUrlHelper
    -0.51
    POSITIVE LOGITS
     sometimes
    1.27
     lately
    1.23
     often
    1.21
     recently
    1.20
     today
    1.16
     Lately
    1.15
    sometimes
    1.14
    recently
    1.14
     Sometimes
    1.14
     Recently
    1.14
    Activations Density 0.368%

    No Known Activations