© 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. 1-GEMMASCOPE-RES-16K
    6. 5899
    Prev
    Next
    INDEX
    Explanations

    specific scientific abbreviations and identifiers within research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.59
    hoeddwyd
    -0.55
     '\\;'
    -0.53
    LElement
    -0.51
     Photocase
    -0.50
     defaultstate
    -0.50
     linkovi
    -0.49
    abestanden
    -0.49
    Personendaten
    -0.48
    URLConnection
    -0.47
    POSITIVE LOGITS
     MH
    1.16
     MW
    1.13
     getM
    1.08
     MB
    1.07
    MH
    1.07
     MG
    1.07
     MV
    1.07
     MMC
    1.07
     MF
    1.07
     MCC
    1.06
    Activations Density 1.352%

    No Known Activations