© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8715
    Prev
    Next
    INDEX
    Explanations

    phrases related to the challenges and considerations of having children and balancing it with personal goals

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

    Follows the word "is" or a form of the verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    mathematical or code structure

    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
    StructEnd
    -0.76
    :✨
    -0.76
    ########.
    -0.68
    MessageOf
    -0.62
     houſe
    -0.61
    OnAdd
    -0.60
     fieldNum
    -0.60
     ſch
    -0.59
    stdafx
    -0.59
    +#+#
    -0.58
    POSITIVE LOGITS
    Rüyada
    0.55
     ujednoznacz
    0.53
    躇
    0.52
    ということは
    0.52
     avviene
    0.51
     betekent
    0.50
    AddHtmlAttribute
    0.50
    misen
    0.49
     feels
    0.48
    UnsafeEnabled
    0.47
    Activations Density 0.292%

    No Known Activations