Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1023
    Prev
    Next
    INDEX
    Explanations

    information related to software availability across different platforms

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

    platform and operating system names (iOS, Android, Windows, Linux, macOS).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tanleria
    -0.40
     Sitzung
    -0.34
    raszam
    -0.34
     herum
    -0.33
     immobilier
    -0.33
     ihti
    -0.32
     cocinar
    -0.32
     reservado
    -0.31
    tamientos
    -0.31
     lleno
    -0.31
    POSITIVE LOGITS
     Windows
    1.63
     Android
    1.57
     Linux
    1.38
     iOS
    1.38
    Windows
    1.37
    Android
    1.34
     macOS
    1.33
     MacOS
    1.32
     android
    1.29
     Macintosh
    1.26
    Activations Density 0.773%

    No Known Activations