© 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. 25-GEMMASCOPE-RES-16K
    11. 4601
    Prev
    Next
    INDEX
    Explanations

    JSON-like structured data or key-value pairs

    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
    eleste
    -0.38
     nakalista
    -0.36
    ContentAsync
    -0.36
    ցված
    -0.34
     useAppContext
    -0.34
     Nicho
    -0.34
    AddTagHelper
    -0.34
     Parcelable
    -0.34
     AssemblyCompany
    -0.33
     تانيه
    -0.33
    POSITIVE LOGITS
     FF
    1.33
     Ff
    1.29
     getF
    1.26
    FF
    1.22
    Ff
    1.20
     FS
    1.15
    Fs
    1.15
     FC
    1.15
    getF
    1.13
     FH
    1.12
    Activations Density 13.109%

    No Known Activations