© 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. 3-GEMMASCOPE-RES-16K
    11. 5837
    Prev
    Next
    INDEX
    Explanations

    Java programming language constructs and API components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.98
    Datuak
    -0.76
     linkovi
    -0.64
     Wicidata
    -0.59
    ụy
    -0.57
     оригіналу
    -0.56
    istoitu
    -0.56
    AxisAlignment
    -0.56
     obyvateľov
    -0.55
    saraba
    -0.55
    POSITIVE LOGITS
    ércoles
    0.55
    AndEndTag
    0.52
    alamu
    0.51
    +#+
    0.51
    ,:]
    0.50
     ATA
    0.50
    Према
    0.50
    dicional
    0.49
    ”]
    0.48
    หวัด
    0.48
    Activations Density 0.070%

    No Known Activations