© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9909
    Prev
    Next
    INDEX
    Explanations

    phrases indicating changes or conditions that are either improving or deteriorating

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

    Following "get" or a form of "get"

    np_acts-logits-general · gemini-2.0-flash

    verb variations of "get"

    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
    IsContent
    -0.65
    providedIn
    -0.64
     analges
    -0.59
    WillAppear
    -0.58
     doccia
    -0.56
     onlyOwner
    -0.55
    IBOutlet
    -0.55
     newArr
    -0.53
     NDEBUG
    -0.51
    prepareStatement
    -0.51
    POSITIVE LOGITS
    Билгалдахарш
    0.85
     attention
    0.64
     GetEnumerator
    0.57
     kasarigan
    0.57
    oriam
    0.57
     geografic
    0.55
     صوتيه
    0.54
     spot
    0.52
     ATTENTION
    0.51
    SBATCH
    0.51
    Activations Density 0.081%

    No Known Activations