© 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. 10-GEMMASCOPE-RES-16K
    11. 10999
    Prev
    Next
    INDEX
    Explanations

    instances of forgetting or neglecting important details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genomen
    -0.75
    styleType
    -0.73
     iArr
    -0.73
    CodedInputStream
    -0.70
    antd
    -0.66
    évaluateur
    -0.65
    MigrationBuilder
    -0.65
     Lans
    -0.65
     naviguant
    -0.65
    SpringBootTest
    -0.63
    POSITIVE LOGITS
     forget
    1.70
     forgotten
    1.65
     forgetting
    1.64
     forgets
    1.61
     FORGET
    1.57
     forgot
    1.51
     Forgotten
    1.47
     Forget
    1.47
    forget
    1.46
    forgotten
    1.38
    Activations Density 0.042%

    No Known Activations