© 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. 5-GEMMASCOPE-RES-16K
    6. 5008
    Prev
    Next
    INDEX
    Explanations

    instances and references to various forms of media and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pickett
    -0.78
    AndEndTag
    -0.71
     WaitForSeconds
    -0.69
     Monsieur
    -0.68
    GetKeyDown
    -0.66
     ngọt
    -0.66
    TypedDataSet
    -0.65
     Parigi
    -0.65
    artement
    -0.65
    izient
    -0.65
    POSITIVE LOGITS
     media
    2.31
     Media
    2.25
     MEDIA
    2.13
    Media
    2.12
    media
    2.08
    MEDIA
    2.04
     medias
    1.74
     Medien
    1.63
     medi
    1.51
    媒体
    1.47
    Activations Density 0.040%

    No Known Activations