© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14852
    Prev
    Next
    INDEX
    Explanations

    references to key points and their associated characteristics or functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.20
     Theſe
    -1.20
     themſelves
    -1.18
     ―――――
    -1.16
     myſelf
    -1.15
     whoſe
    -1.14
     Мексичка
    -1.13
     ſeveral
    -1.13
     ་་
    -1.12
     Anſ
    -1.11
    POSITIVE LOGITS
     keys
    1.78
     key
    1.71
     Keys
    1.65
     Key
    1.60
     KEY
    1.58
    key
    1.54
    KEY
    1.53
    keys
    1.43
     KEYS
    1.39
    Key
    1.35
    Activations Density 0.057%

    No Known Activations