© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4176
    Prev
    Next
    INDEX
    Explanations

    negative phrases and concepts regarding lack or absence

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

    "no" followed by certain words

    np_acts-logits-general · gemini-2.0-flash

    lack of control or idea

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexType
    -0.45
    StoryboardSegue
    -0.43
     Lingkungan
    -0.40
    emment
    -0.40
    mybatisplus
    -0.40
    woordig
    -0.39
     '{@
    -0.39
     Gedicht
    -0.39
     terbatas
    -0.39
    Litteratur
    -0.39
    POSITIVE LOGITS
     EconPapers
    0.49
     control
    0.44
     Савезне
    0.42
     &___
    0.41
     CONTROL
    0.41
     protoimpl
    0.40
    intios
    0.40
     OFDb
    0.40
     controls
    0.38
     contrôle
    0.38
    Activations Density 0.186%

    No Known Activations