© 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. 19-GEMMASCOPE-RES-16K
    6. 495
    Prev
    Next
    INDEX
    Explanations

    terms related to analysis and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.65
    stdc
    -0.64
     HttpNotFound
    -0.62
     eventdata
    -0.59
    Datuak
    -0.55
     كومونز
    -0.55
     cumplido
    -0.55
    BagConstraints
    -0.54
    verwijspagina
    -0.54
    χρι
    -0.53
    POSITIVE LOGITS
     creation
    1.26
     removal
    1.25
     việc
    1.11
     use
    1.09
     preparation
    1.07
     obtaining
    1.05
     determination
    1.02
     introduction
    1.01
    การ
    1.01
    removal
    1.00
    Activations Density 1.349%

    No Known Activations