Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 1951
    Prev
    Next
    INDEX
    Explanations

    terms related to fluid jetting technology and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ️
    -1.11
    ys
    -0.62
    ies
    -0.60
    ity
    -0.59
    ish
    -0.55
    es
    -0.55
    antMatchers
    -0.51
     NgModule
    -0.49
    ers
    -0.48
    iness
    -0.48
    POSITIVE LOGITS
    ting
    2.03
    ted
    1.61
    ters
    1.42
    ter
    1.35
    TING
    1.34
    tings
    1.32
    table
    1.06
    tening
    1.04
    tingly
    1.01
    tering
    1.01
    Activations Density 0.411%

    No Known Activations