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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4771
    Prev
    Next
    INDEX
    Explanations

    terms related to control systems and classification in the context of artificial neural networks

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

    Code, parameters, and technical specifications

    np_acts-logits-general · gemini-2.0-flash

    conventional

    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
    IntoConstraints
    -0.51
     Wikimedijinoj
    -0.49
     betweenstory
    -0.48
     CSRF
    -0.47
    WebElementEntity
    -0.47
    BindingResult
    -0.47
     Untold
    -0.47
     uner
    -0.46
    ernalia
    -0.46
    :][
    -0.45
    POSITIVE LOGITS
     traditional
    0.97
    traditional
    0.86
     conventional
    0.85
     klassische
    0.84
     classic
    0.82
    传统的
    0.82
     klassischen
    0.79
     simple
    0.78
    classic
    0.77
     tradisional
    0.77
    Activations Density 1.234%

    No Known Activations