© 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. 16-GEMMASCOPE-RES-16K
    6. 3899
    Prev
    Next
    INDEX
    Explanations

    references to different models in various contexts

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

    The token "Model" followed by a Roman numeral or parameters

    np_acts-logits-general · gemini-2.0-flash

    model concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Чу
    -0.62
    achten
    -0.60
     Eup
    -0.58
     bapt
    -0.56
    etu
    -0.56
     './../
    -0.56
     religieuse
    -0.55
     Kla
    -0.55
    ignac
    -0.54
     Suzy
    -0.54
    POSITIVE LOGITS
     MODEL
    1.51
     models
    1.41
     Model
    1.34
     model
    1.33
     Models
    1.31
     AspNetCore
    1.28
    Models
    1.28
    MODEL
    1.27
     MODELS
    1.26
    model
    1.22
    Activations Density 0.096%

    No Known Activations