© 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. 14-GEMMASCOPE-RES-16K
    11. 11068
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "target" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CBA
    -0.75
     dysplasia
    -0.72
     CBA
    -0.68
     Jaz
    -0.68
     fistula
    -0.67
    xffffff
    -0.65
     papyrus
    -0.64
     colitis
    -0.64
     Philo
    -0.63
    rophoresis
    -0.61
    POSITIVE LOGITS
     targets
    1.62
     TARGET
    1.52
     Target
    1.50
     Targets
    1.47
    TARGET
    1.44
     target
    1.44
    targets
    1.38
    Target
    1.33
    target
    1.28
     getTarget
    1.27
    Activations Density 0.059%

    No Known Activations