© 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. 1238
    Prev
    Next
    INDEX
    Explanations

    technical terminology and jargon related to industrial processes and methodologies

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

    Followed by determiners or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    another

    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
     صوتيه
    -0.58
    featureID
    -0.57
     surla
    -0.55
    yntaxException
    -0.51
     propOrder
    -0.51
     Meksiku
    -0.50
     StatefulWidget
    -0.50
     naselje
    -0.49
    :✨
    -0.48
    ActionCreators
    -0.48
    POSITIVE LOGITS
     another
    3.30
    another
    2.99
    Another
    2.93
     Another
    2.87
     ANOTHER
    2.24
     otra
    2.16
     otro
    2.14
    另一个
    2.06
    另一個
    2.04
    Otra
    2.02
    Activations Density 0.636%

    No Known Activations