© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    references to the Internet of Things (IoT) and related technologies

    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
    #+#
    -0.79
    AndEndTag
    -0.62
     مشين
    -0.59
    ayne
    -0.56
     AspNetCore
    -0.55
    pania
    -0.54
    ccoli
    -0.54
     <=",
    -0.53
     الحره
    -0.53
    Бахар
    -0.53
    POSITIVE LOGITS
     IoT
    0.77
    AutoScale
    0.59
    IoT
    0.59
     devices
    0.58
     monitoring
    0.56
     sensors
    0.56
     sensing
    0.56
     alarms
    0.55
    裝
    0.55
     alarm
    0.54
    Activations Density 0.269%

    No Known Activations